Contrastive pre-trained vision-language models, such as CLIP, demonstrate strong generalization abilities in zero-shot classification by leveraging embeddings extracted from image and text encoders. This paper aims to robustly fine-tune these vision-language models on in-distribution (ID) data without compromising their generalization abilities in out-of-distribution (OOD) and zero-shot settings. Current robust fine-tuning methods tackle this challenge by reusing contrastive learning, which was used in pre-training, for fine-tuning. However, we found that these methods distort the geometric structure of the embeddings, which plays a crucial role in the generalization of vision-language models, resulting in limited OOD and zero-shot performance. To address this, we propose Difference Vector Equalization (DiVE), which preserves the geometric structure during fine-tuning. The idea behind DiVE is to constrain difference vectors, each of which is obtained by subtracting the embeddings extracted from the pre-trained and fine-tuning models for the same data sample. By constraining the difference vectors to be equal across various data samples, we effectively preserve the geometric structure. Therefore, we introduce two losses: average vector loss (AVL) and pairwise vector loss (PVL). AVL preserves the geometric structure globally by constraining difference vectors to be equal to their weighted average. PVL preserves the geometric structure locally by ensuring a consistent multimodal alignment. Our experiments demonstrate that DiVE effectively preserves the geometric structure, achieving strong results across ID, OOD, and zero-shot metrics.

This paper presents a novel method for automatically recognizing people's apparent personality traits as perceived by others. In previous studies, apparent personality trait recognition from multimodal human behavior is often modeled to directly estimate personality trait scores, i.e., the ``Big Five'' scores. In the model training phase, ground-truth personality trait scores were often determined from personality test results scored by many other people using fine-grained questionnaires, however, rich information in the personality test results have not been leveraged for anything other than determining the ground-truth Big Five scores. The scores assigned to each questionnaire item are thought to include more meta-level differences in personality characteristics. Therefore, we propose joint modeling methods that can estimate not only the Big Five scores but also questionnaire item-level scores. This enables us to improve awareness of multimodal human behavior. In addition, we present a newly created self-introduction video dataset with 50-item Big Five questionnaire results since previous apparent personality trait recognition datasets do not provide such personality test results. Experiments using the created dataset demonstrate that our proposed joint modeling methods with a multimodal transformer backbone can improve to estimate Big Five scores and effectively estimate questionnaire item-level scores. We also verify that the estimation performance reached human evaluation performance.

This paper proposes a personalization method for speech emotion recognition (SER) through in-context learning (ICL). Since the expression of emotions varies from person to person, speaker-specific adaptation is crucial for improving the SER performance. Conventional SER methods have been personalized using emotional utterances of a target speaker, but it is often difficult to prepare utterances corresponding to all emotion labels in advance. Our idea to overcome this difficulty is to obtain speaker characteristics by conditioning a few emotional utterances of the target speaker in ICL-based inference. ICL is a method to perform unseen tasks by conditioning a few inputoutput examples through inference in large language models (LLMs). We meta-train a speech-language model extended from the LLM to learn how to perform personalized SER via ICL. Experimental results using our newly collected SER dataset demonstrate that the proposed method outperforms conventional methods.

This paper proposes a new pre-training method utilizing external text resources to improve the robustness of single-channel multi-talker automatic speech recognition (MTASR) across various linguistic domains. In the development of single-talker ASR systems, various pre-training methods have been studied to acquire knowledge about word order and correspondence between phonetic information and text from external text resources. However, methods focusing on improving MT-ASR performance by leveraging external text resources remain underexplored. To bridge this gap, we aim to acquire the ability to discover multiple texts contained within overlapping phonetic information. The key idea of the proposed method is to induce overlapping phenomena in phoneme sequences in order to reproduce a task similar to MT-ASR using external text resources. Our experiments demonstrate that the proposed method significantly improves the MT-ASR performance on both in-domain and out-of-domain linguistic tasks.

This paper proposes a unified framework, All-in-One ASR, that allows a single model to support multiple automatic speech recognition (ASR) paradigms, including connectionist temporal classification (CTC), attention-based encoder-decoder (AED), and Transducer, in both offline and streaming modes. While each ASR architecture offers distinct advantages and trade-offs depending on the application, maintaining separate models for each scenario incurs substantial development and deployment costs. To address this issue, we introduce a multi-mode joiner that enables seamless integration of various ASR modes within a single unified model. Experiments show that All-in-One ASR significantly reduces the total model footprint while matching or even surpassing the recognition performance of individually optimized ASR models. Furthermore, joint decoding leverages the complementary strengths of different ASR modes, yielding additional improvements in recognition accuracy.

This study investigates the talking face generation method to convert a speaker’s video to give a target impression, such as “favorable” or “considerate”. Such an impression conversion method needs to consider the input speech semantics because they affect the impression of a speaker’s video along with the facial expression. Conventional emotional talking face generation methods utilize speech information to synchronize the lip and speech of the output video. However, they cannot consider speech semantics because the speech representations contain only phonetic information. To solve this problem, we propose a facial expression conversion model that uses a semantic vector obtained from BERT embeddings of speech recognition results of input speech. We first constructed an audio-visual dataset with impression labels assigned to each utterance. The evaluation results based on the dataset showed that the proposed method could improve the estimation accuracy of the facial expressions of the target video.

Self-supervised learning (SSL) has been dramatically successful not only in monolingual but also in cross-lingual settings. However, since the two settings have been studied individually in general, there has been little research focusing on how effective a cross-lingual model is in comparison with a monolingual model. In this paper, we investigate this fundamental question empirically with Japanese automatic speech recognition (ASR) tasks. First, we begin by comparing the ASR performance of cross-lingual and monolingual models for two different language tasks while keeping the acoustic domain as identical as possible. Then, we examine how much unlabeled data collected in Japanese is needed to achieve performance comparable to a cross-lingual model pre-trained with tens of thousands of hours of English and/or multilingual data. Finally, we extensively investigate the effectiveness of SSL in Japanese and demonstrate state-of-the-art performance on multiple ASR tasks. Since there is no comprehensive SSL study for Japanese, we hope this study will guide Japanese SSL research.

End-to-end speech summarization (E2E SSum) is a technique to directly generate summary sentences from speech. Compared with the cascade approach, which combines automatic speech recognition (ASR) and text summarization models, the E2E approach is more promising because it mitigates ASR errors, incorporates nonverbal information, and simplifies the overall system. However, since collecting a large amount of paired data (i.e., speech and summary) is difficult, the training data is usually insufficient to train a robust E2E SSum system. In this paper, we present two novel methods that leverage a large amount of external text summarization data for E2E SSum training. The first technique is to utilize a text-to-speech (TTS) system to generate synthesized speech, which is used for E2E SSum training with the text summary. The second is a TTS-free method that directly inputs phoneme sequence instead of synthesized speech to the E2E SSum model. Experiments show that our proposed TTS- and phoneme-based methods improve several metrics on the How2 dataset. In particular, our best system outperforms a previous state-of-the-art one by a large margin (i.e., METEOR score improvements of more than 6 points). To the best of our knowledge, this is the first work to use external language resources for E2E SSum. Moreover, we report a detailed analysis of the How2 dataset to confirm the validity of our proposed E2E SSum system.

The recurrent neural network-transducer (RNNT) is a promising approach for automatic speech recognition (ASR) with the introduction of a prediction network that autoregressively considers linguistic aspects. To train the autoregressive part, the ground-truth tokens are used as substitutions for the previous output token, which leads to insufficient robustness to incorrect past tokens; a recognition error in the decoding leads to further errors. Scheduled sampling (SS) is a technique to train autoregressive model robustly to past errors by randomly replacing some ground-truth tokens with actual outputs generated from a model. SS mitigates the gaps between training and decoding steps, known as exposure bias, and it is often used for attentional encoder-decoder training. However SS has not been fully examined for RNNT because of the difficulty in applying SS to RNNT due to the complicated RNNT output form. In this paper we propose SS approaches suited for RNNT. Our SS approaches sample the tokens generated from the distiribution of RNNT itself, i.e. internal language model or RNNT outputs. Experiments in three datasets confirm that RNNT trained with our SS approach achieves the best ASR performance. In particular, on a Japanese ASR task, our best system outperforms the previous state-of-the-art alternative.

In this paper, we propose novel cross-lingual self-supervised speech representation learning methods that explicitly consider language information. Cross-lingual self-supervised speech representation learning has been studied to make effective use of diverse data in various languages. Previous methods train models from multilingual datasets without taking language into account. However, it is difficult to train speech representations from multilingual datasets in the same space without language specification since there are clear differences in the acoustic context between languages. To solve this problem, we propose leveraging language IDs to build self-supervised speech representation learning models that explicitly consider language information. Our proposed models utilize fixed-dimensional language embeddings converted from language IDs for the model learning the relationship between related speech representations in different languages. We investigate two strategies to introduce language embeddings into the models: adding the embeddings to all of the inputs and concatenating to the inputs of the Transformer. We experimentally investigated how the difference between the two strategies affects the downstream tasks. Experimental results on the English and Japanese datasets show that the proposed methods improve the accuracies of downstream automatic speech recognition tasks.

In Siamese-network-based self-supervised learning (SSL), multilevel supervision (MLS) is a natural extension to enforce intermediate representations’ consistency against data augmentations. Although existing studies have incorporated MLS to boost their system performances in combination with other ideas, vanilla MLS has not been deeply analyzed. Here, we extensively investigate how MLS works and how much impact it has on SSL performance with various training settings to understand the effectiveness of MLS by itself. For this investigation, we develop a simple Siamese-SSL-based MLS framework Ladder Siamese Network, equipped with multi-level, non-contrastive, and global/local self-supervised training losses. We show that the proposed framework can simultaneously improve BYOL baselines in classification, detection, and segmentation solely by adding MLS. In comparison with the state-of-the-art methods, our Ladder-based model achieves competitive and balanced performances in all tested benchmarks without causing large degradation in any of them, which suggests the usability for building a multi-purpose backbone.

This paper presents a novel multi-perspective document revision task. In conventional studies on document revision, tasks such as grammatical error correction, sentence reordering, and discourse relation classification have been performed individually; however, these tasks simultaneously should be revised to improve the readability and clarity of a whole document. Thus, our study defines multi-perspective document revision as a task that simultaneously revises multiple perspectives. To model the task, we design a novel Japanese multi-perspective document revision dataset that simultaneously handles seven perspectives to improve the readability and clarity of a document. Although a large amount of data that simultaneously handles multiple perspectives is needed to model multi-perspective document revision elaborately, it is difficult to prepare such a large amount of this data. Therefore, our study offers a multi-perspective document revision modeling method that can use a limited amount of matched data (i.e., data for the multi-perspective document revision task) and external partially-matched data (e.g., data for the grammatical error correction task). Experiments using our created dataset demonstrate the effectiveness of using multiple partially-matched datasets to model the multi-perspective document revision task.

In this paper we propose improvements to our recently proposed hybrid RNN-T/Attention architecture that includes a shared encoder followed by recurrent neural network-transducer (RNN-T) and triggered attention-based decoders (TAD). The use of triggered attention enables the attention-based decoder (AD) to operate in a streaming manner. When a trigger point is detected by RNN-T, TAD uses the context from the start-of-speech up to that trigger point to compute the attention weights. Consequently, the computation costs and the memory consumptions are quadratically increased with the duration of the utterances because all input features must be stored and used to re-compute the attention weights. In this paper, we use a short context from a few frames prior to each trigger point for attention weight computation resulting in reduced computation and memory costs. We call the proposed framework triggered chunkwise AD (TCAD). We also investigate the effectiveness of internal language model (ILM) estimation approach using both ILMs of RNN-T and TCAD heads for improving RNN-T performance. We confirm in experiments with public and private datasets covering various scenarios that TCAD achieves superior recognition performance while reducing computation costs compared to TAD.

Target speech extraction is a technique to extract the target speaker's voice from mixture signals using a pre-recorded enrollment utterance that characterize the voice characteristics of the target speaker.One major difficulty of target speech extraction lies in handling variability in "intra-speaker" characteristics, i.e., characteristics mismatch between target speech and an enrollment utterance.While most conventional approaches focus on improving average performance given a set of enrollment utterances, here we propose to guarantee the worst performance, which we believe is of great practical importance.In this work, we propose an evaluation metric called worstenrollment source-to-distortion ratio (SDR) to quantitatively measure the robustness towards enrollment variations.We also introduce a novel training scheme that aims at directly optimizing the worst-case performance by focusing on training with difficult enrollment cases where extraction does not perform well.In addition, we investigate the effectiveness of auxiliary speaker identification loss (SI-loss) as another way to improve robustness over enrollments.Experimental validation reveals the effectiveness of both worst-enrollment target training and SI-loss training to improve robustness against enrollment variations, by increasing speaker discriminability.

This paper presents a novel knowledge distillation method for dialogue sequence labeling. Dialogue sequence labeling is a supervised learning task that estimates labels for each utterance in the target dialogue document, and is useful for many applications such as dialogue act estimation. Accurate labeling is often realized by a hierarchically-structured large model consisting of utterance-level and dialogue-level networks that capture the contexts within an utterance and between utterances, respectively. However, due to its large model size, such a model cannot be deployed on resource-constrained devices. To overcome this difficulty, we focus on knowledge distillation which trains a small model by distilling the knowledge of a large and high performance teacher model. Our key idea is to distill the knowledge while keeping the complex contexts captured by the teacher model. To this end, the proposed method, hierarchical knowledge distillation, trains the small model by distilling not only the probability distribution of the label classification, but also the knowledge of utterance-level and dialogue-level contexts trained in the teacher model by training the model to mimic the teacher model's output in each level. Experiments on dialogue act estimation and call scene segmentation demonstrate the effectiveness of the proposed method.

This paper presents a self-supervised learning method for pointer-generator networks to improve spoken-text normalization. Spoken-text normalization that converts spoken-style text into style normalized text is becoming an important technology for improving subsequent processing such as machine translation and summarization. The most successful spoken-text normalization method to date is sequence-to-sequence (seq2seq) mapping using pointer-generator networks that possess a copy mechanism from an input sequence. However, these models require a large amount of paired data of spoken-style text and style normalized text, and it is difficult to prepare such a volume of data. In order to construct spoken-text normalization model from the limited paired data, we focus on self-supervised learning which can utilize unpaired text data to improve seq2seq models. Unfortunately, conventional self-supervised learning methods do not assume that pointer-generator networks are utilized. Therefore, we propose a novel self-supervised learning method, MAsked Pointer-Generator Network (MAPGN). The proposed method can effectively pre-train the pointer-generator net-work by learning to fill masked tokens using the copy mechanism. Our experiments demonstrate that MAPGN is more effective for pointer-generator networks than the conventional self-supervised learning methods in two spoken-text normalization tasks.

We present an audio-visual speech separation learning method that considers the correspondence between the separated signals and the visual signals to reflect the speech characteristics during training. Audio-visual speech separation is a technique to estimate the individual speech signals from a mixture using the visual signals of the speakers. Conventional studies on audio-visual speech separation mainly train the separation model on the audio-only loss, which reflects the distance between the source signals and the separated signals. However, conventional losses do not reflect the characteristics of the speech signals, including the speaker’s characteristics and phonetic information, which leads to distortion or remaining noise. To address this problem, we propose the cross-modal correspondence (CMC) loss, which is based on the cooccurrence of the speech signal and the visual signal. Since the visual signal is not affected by background noise and contains speaker and phonetic information, using the CMC loss enables the audio-visual speech separation model to remove noise while preserving the speech characteristics. Experimental results demonstrate that the proposed method learns the cooccurrence on the basis of CMC loss, which improves separation performance.

We present a novel large-context end-to-end automatic speech recognition (E2E-ASR) model and its effective training method based on knowledge distillation. Common E2E-ASR models have mainly focused on utterance-level processing in which each utterance is independently transcribed. On the other hand, large-context E2E-ASR models, which take into account long-range sequential contexts beyond utterance boundaries, well handle a sequence of utterances such as discourses and conversations. However, the transformer architecture, which has recently achieved state-of-the-art ASR performance among utterance-level ASR systems, has not yet been introduced into the large-context ASR systems. We can expect that the transformer architecture can be leveraged for effectively capturing not only input speech contexts but also long-range sequential contexts beyond utterance boundaries. Therefore, this paper proposes a hierarchical transformer-based large-context E2E-ASR model that combines the transformer architecture with hierarchical encoder-decoder based large-context modeling. In addition, in order to enable the proposed model to use long-range sequential contexts, we also propose a large-context knowledge distillation that distills the knowledge from a pre-trained large-context language model in the training phase. We evaluate the effectiveness of the proposed model and proposed training method on Japanese discourse ASR tasks.

Recurrent neural network-transducer (RNN-T) is promising for building time-synchronous end-to-end automatic speech recognition (ASR) systems, in part because it does not need frame-wise alignment between input features and target labels in the training step. Although training without alignment is beneficial, it makes it difficult to discern the relation between input features and output token sequences. This, in effect, degrades RNN-T performance. Our solution is SimpleFlat (SF), a novel and simple whole-network pretraining approach for RNN-T. SF extracts frame-wise alignments on-the-fly from the training dataset, and does not require any external resources. We distribute equal numbers of target tokens to each frame following RNN-T encoder output lengths by repeating each token. The frame-wise tokens so created are shifted, and also used as the prediction network inputs. Therefore, SF can be implemented by cross entropy loss computation as in autoregressive model training. Experiments on Japanese and English ASR tasks demonstrate that SF can effectively improve various RNN-T architectures.

In this paper, we propose a novel spoken-text-style conversion method that can simultaneously execute multiple style conversion modules such as punctuation restoration and disfluency deletion without preparing matched datasets.In practice, transcriptions generated by automatic speech recognition systems are not highly readable because they often include many disfluencies and do not include punctuation marks.To improve their readability, multiple spoken-text-style conversion modules that individually model a single conversion task are cascaded because matched datasets that simultaneously handle multiple conversion tasks are often unavailable.However, the cascading is unstable against the order of tasks because of the chain of conversion errors.Besides, the computation cost of the cascading must be higher than the single conversion.To execute multiple conversion tasks simultaneously without preparing matched datasets, our key idea is to distinguish individual conversion tasks using the on-off switch.In our proposed zero-shot joint modeling, we switch the individual tasks using multiple switching tokens, enabling us to utilize a zero-shot learning approach to executing simultaneous conversions.Our experiments on joint modeling of disfluency deletion and punctuation restoration demonstrate the effectiveness of our method.

We present a novel personalized voice activity detection (PVAD) learning method that does not require enrollment data during training.PVAD is a task to detect the speech segments of a specific target speaker at the frame level using enrollment speech of the target speaker.Since PVAD must learn speakers' speech variations to clarify the boundary between speakers, studies on PVAD used large-scale datasets that contain many utterances for each speaker.However, the datasets to train a PVAD model are often limited because substantial cost is needed to prepare such a dataset.In addition, we cannot utilize the datasets used to train the standard VAD because they often lack speaker labels.To solve these problems, our key idea is to use one utterance as both a kind of enrollment speech and an input to the PVAD during training, which enables PVAD training without enrollment speech.In our proposed method, called enrollment-less training, we augment one utterance so as to create variability between the input and the enrollment speech while keeping the speaker identity, which avoids the mismatch between training and inference.Our experimental results demonstrate the efficacy of the method.

In this paper, we present a novel modeling method for singlechannel multi-talker overlapped automatic speech recognition (ASR) systems.Fully neural network based end-to-end models have dramatically improved the performance of multi-taker overlapped ASR tasks.One promising approach for end-toend modeling is autoregressive modeling with serialized output training in which transcriptions of multiple speakers are recursively generated one after another.This enables us to naturally capture relationships between speakers.However, the conventional modeling method cannot explicitly take into account the speaker attributes of individual utterances such as gender and age information.In fact, the performance deteriorates when each speaker is the same gender or is close in age.To address this problem, we propose unified autoregressive modeling for joint end-to-end multi-talker overlapped ASR and speaker attribute estimation.Our key idea is to handle gender and age estimation tasks within the unified autoregressive modeling.In the proposed method, transformer-based autoregressive model recursively generates not only textual tokens but also attribute tokens of each speaker.This enables us to effectively utilize speaker attributes for improving multi-talker overlapped ASR.Experiments on Japanese multi-talker overlapped ASR tasks demonstrate the effectiveness of the proposed method.

We propose a cross-modal transformer-based neural correction models that refines the output of an automatic speech recognition (ASR) system so as to exclude ASR errors.Generally, neural correction models are composed of encoder-decoder networks, which can directly model sequence-to-sequence mapping problems.The most successful method is to use both input speech and its ASR output text as the input contexts for the encoder-decoder networks.However, the conventional method cannot take into account the relationships between these two different modal inputs because the input contexts are separately encoded for each modal.To effectively leverage the correlated information between the two different modal inputs, our proposed models encode two different contexts jointly on the basis of cross-modal self-attention using a transformer.We expect that cross-modal self-attention can effectively capture the relationships between two different modals for refining ASR hypotheses.We also introduce a shallow fusion technique to efficiently integrate the first-pass ASR model and our proposed neural correction model.Experiments on Japanese natural language ASR tasks demonstrated that our proposed models achieve better ASR performance than conventional neural correction models.

We propose a semi-supervised learning method for building end-to-end rich transcription-style automatic speech recognition (RT-ASR) systems from small-scale rich transcriptionstyle and large-scale common transcription-style datasets.In spontaneous speech tasks, various speech phenomena such as fillers, word fragments, laughter and coughs, etc. are often included.While common transcriptions do not give special awareness to these phenomena, rich transcriptions explicitly convert them into special phenomenon tokens as well as textual tokens.In previous studies, the textual and phenomenon tokens were simultaneously estimated in an end-to-end manner.However, it is difficult to build accurate RT-ASR systems because large-scale rich transcription-style datasets are often unavailable.To solve this problem, our training method uses a limited rich transcription-style dataset and common transcriptionstyle dataset simultaneously.The Key process in our semisupervised learning is to convert the common transcription-style dataset into a pseudo-rich transcription-style dataset.To this end, we introduce style tokens which control phenomenon tokens are generated or not into transformer-based autoregressive modeling.We use this modeling for generating the pseudorich transcription-style datasets and for building RT-ASR system from the pseudo and original datasets.Our experiments on spontaneous ASR tasks showed the effectiveness of the proposed method.

This paper presents a novel training method for end-to-end scene text recognition. End-to-end scene text recognition offers high recognition accuracy, especially when using the encoder-decoder model based on Transformer. To train a highly accurate end-to-end model, we need to prepare a large image-to-text paired dataset for the target language. However, it is difficult to collect this data, especially for resource-poor languages. To overcome this difficulty, our proposed method utilizes well-prepared large datasets in resource-rich languages such as English, to train the resource-poor encoder-decoder model. Our key idea is to build a model in which the encoder reflects knowledge of multiple languages while the decoder specializes in knowledge of just the resource-poor language. To this end, the proposed method pre-trains the encoder by using a multilingual dataset that combines the resource-poor language’s dataset and the resource-rich language’s dataset to learn language-invariant knowledge for scene text recognition. The proposed method also pre-trains the decoder by using the resource-poor language’s dataset to make the decoder better suited to the resource-poor language. Experiments on Japanese scene text recognition using a small, publicly available dataset demonstrate the effectiveness of the proposed method.

This paper presents a novel self-supervised learning method for handling conversational documents consisting of transcribed text of human-to-human conversations. One of the key technologies for understanding conversational documents is utterance-level sequential labeling, where labels are estimated from the documents in an utterance-by-utterance manner. The main issue with utterance-level sequential labeling is the difficulty of collecting labeled conversational documents, as manual annotations are very costly. To deal with this issue, we propose large-context conversational representation learning (LC-CRL), a self-supervised learning method specialized for conversational documents. A self-supervised learning task in LC-CRL involves the estimation of an utterance using all the surrounding utterances based on large-context language modeling. In this way, LC-CRL enables us to effectively utilize unlabeled conversational documents and thereby enhances the utterance-level sequential labeling. The results of experiments on scene segmentation tasks using contact center conversational datasets demonstrate the effectiveness of the proposed method.

The process of spoken-language acquisition has been one of the topics of greatest interest to linguists for decades. By uti-lizing modern machine learning techniques, we simulated this process on computers, which helps to understand it and develop new possibilities of applying this concept on intelligent robots, among other things. This paper proposes a new framework for simulating spoken-language acquisition by combining reinforcement learning and unsupervised learning methods. Our experiments also show that a spoken language can be acquired considerably faster by identifying potential word segments from collected ambient sounds in an unsupervised manner.

We present a novel training approach for connectionist temporal classification (CTC) -based automatic speech recognition (ASR) systems. CTC models are promising for building both a conventional acoustic model and an end-to-end (E2E) ASR model. However, CTC models make it difficult to capture the correct timing of each output label because timing is not given explicitly in the training data. In this paper, we propose a new auxiliary task with frame-wise targets for CTC model enhancement. We utilize attention weights generated by an attention-based encoder-decoder model (S2S) for making the targets, called the attention matrix. The attention matrix is the sum of the products of the attention weights (spike timing information) and the corresponding target vectors (probability information), and used for S2S-to-CTC knowledge distillation loss computation. Therefore, the attention matrix makes the CTC models jointly train-able as regards spike timings and their posteriors. Experiments on Japanese ASR tasks demonstrate that our proposal is effective for CTC model training; it achieves a 10.2% (E2E) / 9.4% (acoustic model) relative reduction in the character/kana-syllable error rates compared to models trained using only CTC loss.

Humans easily and routinely identify an image region that corresponds to an observed sound in their daily lives. The task is formulated as an unsupervised sound source localization without using tagged data. Recently, several methods have been proposed that utilize the activation of hidden or output layers of neural networks, such as an attention layer or feature maps in a convolutional neural network (CNN). We propose another strategy that obtains a localization map at the input side, applying the widely used input gradient method. It is computationally efficient and can be easily applied to any existing techniques because it is free from the network structure. Taking advantage of it, we propose a combination method with existing methods for higher sound localization performance. Experiments are performed using the Flickr-SoundNet data set. When a pre-trained image front-end was used, the proposed method gives better results than the attention-based method. For a completely unsupervised condition, the gradient method provides comparable performance as the conventional methods; the best results are obtained by this combination method.

This paper presents a novel fusion method for integrating an external language model (LM) into the Transformer based sequenceto-sequence (seq2seq) model.While paired data are basically required to train the seq2seq model, the external LM can be trained with only unpaired data.Thus, it is important to leverage memorized knowledge in the external LM for building the seq2seq model, since it is hard to prepare a large amount of paired data.However, the existing fusion methods assume that the LM is integrated with recurrent neural network-based seq2seq models instead of the Transformer.Therefore, this paper proposes a fusion method that can explicitly utilize network structures in the Transformer.The proposed method, called memory attentive fusion, leverages the Transformer-style attention mechanism that repeats source-target attention in a multi-hop manner for reading the memorized knowledge in the LM.Our experiments on two text-style conversion tasks demonstrate that the proposed method performs better than conventional fusion methods.

This paper presents a novel training method for speech-based end-of-turn detection for which not only manually annotated speech data sets but also punctuated text data sets are utilized. The speech-based end-of-turn detection estimates whether a target speaker's utterance is ended or not using speech information. In previous studies, the speech-based end-of-turn detection models were trained using only speech data sets that contained manually annotated end-of-turn labels. However, since the amounts of annotated speech data sets are often limited, the end-of-turn detection models were unable to correctly handle a wide variety of speech patterns. In order to mitigate the data scarcity problem, our key idea is to leverage punctuated text data sets for building more effective speech-based end-of-turn detection. Therefore, the proposed method introduces cross-modal representation learning to construct a speech encoder and a text encoder that can map speech and text with the same lexical information into similar vector representations. This enables us to train speech-based end-of-turn detection models from the punctuated text data sets by tackling text-based sentence boundary detection. In experiments on contact center calls, we show that speech-based end-of-turn detection models using hierarchical recurrent neural networks can be improved through the use of punctuated text data sets.

This paper presents a generalized form of large-context language models (LCLMs) that can take linguistic contexts beyond utterance boundaries into consideration. In discourse-level and conversation-level automatic speech recognition (ASR) tasks, which have to handle a series of utterances, it is essential to capture long-range linguistic contexts beyond utterance boundaries. The LCLMs of previous studies mainly focused on utilizing past contexts, and none fully utilized future contexts because LMs typically process words in a time-ordered manner. Our key idea is to introduce the LCLMs into the situation where ASR results of the whole series of utterances are given by a first decoding pass. This situation makes it possible for the LCLMs to leverage future contexts. In this paper, we propose generalized LCLMs (GLCLMs) based on forward-backward hierarchical recurrent encoder-decoder models in which generative probabilities of individual utterances are computed by leveraging not only past contexts but also future contexts beyond utterance boundaries. In order to efficiently introduce GLCLMs to ASR, we also propose a global-context iterative rescoring method that repeatedly rescores the ASR hypotheses of an individual utterance by using surrounding ASR hypotheses. Experiments on discourse-level ASR tasks demonstrate the effectiveness of our GLCLM approach.

For continuous keyword detection, the advantage of dynamic programming (DP) matching is that it can detect any keyword without re-training the system. In previous research, higher detection accuracy was reported using 2D-RNN based DP matching than using conventional DP and embedding methods. However, 2D-RNN based DP matching has a high computational cost. In order to address this problem, we combine a convolutional neural network (CNN) and 2D-RNN based DP matching into a unified framework which, based on the kernel size and the number of CNN layers, has a polynomial order effect on reducing the computational cost. Experimental results, using Google Speech Commands Dataset and the CHiME-3 challenge's noise data, demonstrate that our proposed model improves open keyword detection performance, compared to the embedding-based baseline system, while it is nine times faster than previous 2D-RNN DP matching.

This paper describes a novel end-to-end automatic speech recognition (ASR) method that takes into consideration long-range sequential context information beyond utterance boundaries. In spontaneous ASR tasks such as those for discourses and conversations, the input speech often comprises a series of utterances. Accordingly, the relationships between the utterances should be leveraged for transcribing the individual utterances. While most previous end-to-end ASR methods only focus on utterance-level ASR that handles single utterances independently, the proposed method (which we call "large-context end-to-end ASR") can explicitly utilize relationships between a current target utterance and all preceding utterances. The method is modeled by combining an attention-based encoder-decoder model, which is one of the most representative end-to-end ASR models, with hierarchical recurrent encoder-decoder models, which are effective language models for capturing long-range sequential contexts beyond the utterance boundaries. Experiments on Japanese discourse speech tasks demonstrate the proposed method yields significant ASR performance improvements compared with the conventional utterance-level end-to-end ASR system.

The state-of-the-art large vocabulary speech recognition systems consist of several components including hidden Markov model and deep neural network. To realize the highest recognition performance, numerous meta-parameters specifying the designs and training setups of these components must be optimized. A prominent obstacle in system development is the laborious effort required by human experts in tuning these meta-parameters. To automate the process, we propose to tune the meta-parameters of a whole large vocabulary speech recognition system using the evolution strategy with a multi-objective Pareto optimization. As the result of the evolution, the system is optimized for both low word error rate and compact model size. Since the approach requires repeated training and evaluation of the recognition systems that require large computation, we make use of parallel computation on cloud computers. Experimental results show the effectiveness of the proposed approach by discovering appropriate configuration for large vocabulary speech recognition systems automatically.

This paper is an initial study on multi-task and multi-lingual joint learning for lexical utterance classification. A major problem in constructing lexical utterance classification modules for spoken dialogue systems is that individual data resources are often limited or unbalanced among tasks and/or languages. Various studies have examined joint learning using neural-network based shared modeling; however, previous joint learning studies focused on either cross-task or cross-lingual knowledge transfer. In order to simultaneously support both multi-task and multi-lingual joint learning, our idea is to explicitly divide state-of-the-art neural lexical utterance classification into language-specific components that can be shared between different tasks and task-specific components that can be shared between different languages. In addition, in order to effectively transfer knowledge between different task data sets and different language data sets, this paper proposes a partially-shared modeling method that possesses both shared components and components specific to individual data sets. We demonstrate the effectiveness of proposed method using Japanese and English data sets with three different lexical utterance classification tasks.

This paper proposes a fully neural network based dialogue-context online end-of-turn detection method that can utilize longrange interactive information extracted from both target speaker's and interlocutor's utterances.In the proposed method, we combine multiple time-asynchronous long short-term memory recurrent neural networks, which can capture target speaker's and interlocutor's multiple sequential features, and their interactions.On the assumption of applying the proposed method to spoken dialogue systems, we introduce target speaker's acoustic sequential features and interlocutor's linguistic sequential features, each of which can be extracted in an online manner.Our evaluation confirms the effectiveness of taking dialogue context formed by the target speaker's utterances and interlocutor's utterances into consideration.

Long short-term memory (LSTM) recurrent neural network based language models are known to improve speech recognition performance. However, significant effort is required to optimize network structures and training configurations. In this study, we automate the development process using evolutionary algorithms. In particular, we apply the covariance matrix adaptation-evolution strategy (CMA-ES), which has demonstrated robustness in other black box hyper-parameter optimization problems. By flexibly allowing optimization of various meta-parameters including layer wise unit types, our method automatically finds a configuration that gives improved recognition performance. Further, by using a Pareto based multi-objective CMA-ES, both WER and computational time were reduced jointly: after 10 generations, relative WER and computational time reductions for decoding were 4.1% and 22.7% respectively, compared to an initial baseline system whose WER was 8.7%.

When building a state-of-the-art speech recognition system, the laborious effort required by human experts in tuning numerous parameters remains a prominent obstacle. The goal of this paper is to automate the process. We propose to tune DNN-HMM based large vocabulary speech recognition systems using the covariance matrix adaptation evolution strategy (CMA-ES) with a multi-objective Pareto optimization. This optimizes systems to achieve both high-accuracy and compact model size. An additional advantage of our approach is that it is efficiently parallelizable and easily adapted to cloud computing services. We performed experiments on the Corpus of Spontaneous Japanese (CSJ) using the TSUBAME 2.5 supercomputer. Compared with a strong manually tuned configuration borrowed from a similar system, our approach automatically discovered systems with lower WER by 0.48%, and systems with 59% smaller model size while keeping WER constant. The optimized training script is released in the Kaldi speech recognition toolkit as the first publicly available recipe for Japanese large vocabulary speech recognition.

This paper describes our Trax game engine developed for the FPGA design competition associated with the 2015 International Conference on Field Programmable Technology (FPT'15). We use path and edge for managing the board information in the game engine. Our game engine recognizes victory conditions such as loop and victory line by using path and edge, and also detects loop attack that is a condition where it is possible to form a loop during the next player's turn. In this paper, we describe the our developed game engine using path and edge.

Co-translational folding (CTF) facilitates correct folding in vivo, but its precise mechanism remains elusive. For the CTF of a three-domain protein SufI, it was reported that the translational attenuation is obligatory to acquire the functional state. Here, to gain structural insights on the underlying mechanisms, we performed comparative molecular simulations of SufI that mimic CTF as well as refolding schemes. A CTF scheme that relied on a codon-based prediction of translational rates exhibited folding probability markedly higher than that by the refolding scheme. When the CTF schedule is speeded up, the success rate dropped. These agree with experiments. Structural investigation clarified that misfolding of the middle domain was much more frequent in the refolding scheme than that in the codon-based CTF scheme. The middle domain is less stable and can fold via interactions with the folded N-terminal domain. Folding pathway networks showed the codon-based CTF gives narrower pathways to the native state than the refolding scheme.

There is a growing demand for daily heart rate (HR) monitoring in the fields of healthcare, fitness, activity recognition, and entertainment. Although various HR monitoring systems have been proposed, most of these employ a wearable device, which may be a burden and disturb one's daily living.

This paper describes a technique for estimating fundamental frequency of speech based on instantaneous frequency (IF). In the technique, fundamental frequency of a signal is obtained by evaluating its IF amplitude spectrum. We define a measure which represents how clearly the harmonic structure is shown in the IF amplitude spectrum. This harmonicity measure is used to select an optimal frequency band on which the IF amplitude spectrum is evaluated. We show the results of fundamental frequency estimation experiments using a speech database which contains 14 male and 14 female speakers' utterances. It is seen that the proposed technique can decrease gross errors substantially and obtain better performance than the conventional method based on the IF amplitude spectrum.