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 paper proposes a guided speaker embedding extraction system, which extracts speaker embeddings of the target speaker using speech activities of target and interference speakers as clues. Several methods for long-form overlapped multi-speaker audio processing are typically two-staged: i) segment-level processing and ii) inter-segment speaker matching. Speaker embeddings are often used for the latter purpose. Typical speaker embedding extraction approaches only use single-speaker intervals to avoid corrupting the embeddings with speech from interference speakers. However, this often makes speaker embeddings impossible to extract because sufficiently long non-overlapping intervals are not always available. In this paper, we propose using speaker activities as clues to extract the embedding of the speaker-of-interest directly from overlapping speech. Specifically, we concatenate the activity of target and non-target speakers to acoustic features before being fed to the model. We also condition the attention weights used for pooling so that the attention weights of the intervals in which the target speaker is inactive are zero. The effectiveness of the proposed method is demonstrated in speaker verification and speaker diarization.

Extending the RNN Transducer (RNNT) to recognize multi-talker speech is essential for wider automatic speech recognition (ASR) applications. Multi-talker RNNT (MT-RNNT) aims to achieve recognition without relying on costly front-end source separation. MT-RNNT is conventionally implemented using architectures with multiple encoders or decoders, or by serializing all speakers’ transcriptions into a single output stream. The first approach is computationally expensive, particularly due to the need for multiple encoder processing. In contrast, the second approach involves a complex label generation process, requiring accurate timestamps of all words spoken by all speakers in the mixture, obtained from an external ASR system. In this paper, we propose a novel alignment-free training scheme for the MT-RNNT (MT-RNNT-AFT) that adopts the standard RNNT architecture. The target labels are created by appending a prompt token corresponding to each speaker at the beginning of the transcription, reflecting the order of each speaker’s appearance in the mixtures. Thus, MT-RNNT-AFT can be trained without relying on accurate alignments, and it can recognize all speakers’ speech with just one round of encoder processing. Experiments show that MT-RNNT-AFT achieves performance comparable to that of the state-of-the-art alternatives, while greatly simplifying the training process.

The zero-shot text-to-speech (TTS) method, based on speaker embeddings extracted from reference speech using self-supervised learning (SSL) speech representations, can reproduce speaker characteristics very accurately. However, this approach suffers from degradation in speech synthesis quality when the reference speech contains noise. In this paper, we propose a noise-robust zero-shot TTS method. We incorporated adapters into the SSL model, which we fine-tuned with the TTS model using noisy reference speech. In addition, to further improve performance, we adopted a speech enhancement (SE) front-end. With these improvements, our proposed SSL-based zero-shot TTS achieved high-quality speech synthesis with noisy reference speech. Through the objective and subjective evaluations, we confirmed that the proposed method is highly robust to noise in reference speech, and effectively works in combination with SE.

Jointly training a speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end has been investigated as a way to mitigate the influence of processing distortion generated by single-channel SE on ASR. In this paper, we investigate the effect of such joint training on the signal-level characteristics of the enhanced signals from the viewpoint of the decomposed noise and artifact errors. The experimental analyses provide two novel findings: 1) ASR-level training of the SE front-end reduces the artifact errors while increasing the noise errors, and 2) simply interpolating the enhanced and observed signals, which achieves a similar effect of reducing artifacts and increasing noise, improves ASR performance without jointly modifying the SE and ASR modules, even for a strong ASR back-end using a WavLM feature extractor. Our findings provide a better understanding of the effect of joint training and a novel insight for designing an ASR agnostic SE front-end.

Target-speaker speech processing (TS) tasks, such as target-speaker automatic speech recognition (TS-ASR), target speech extraction (TSE), and personal voice activity detection (p-VAD), are important for extracting information about a desired speaker’s speech even when it is corrupted by interfering speakers. While most studies have focused on training schemes or system architectures for each specific task, the auxiliary network for embedding target-speaker cues has not been investigated comprehensively in a unified crosstask evaluation. Therefore, this paper aims to address a fundamental question: what is the preferred speaker embedding for TS tasks? To this end, for the TS-ASR, TSE, and p-VAD tasks, we compare pre-trained speaker encoders (i.e., self-supervised or speaker recognition models) that compute speaker embeddings from pre-recorded enrollment speech of the target speaker with ideal speaker embeddings derived directly from the target speaker’s identity in the form of a one-hot vector. To further understand the properties of ideal speaker embedding, we optimize it using a gradient-based approach to improve performance on the TS task. Our analysis reveals that speaker verification performance is somewhat unrelated to TS task performances, the one-hot vector outperforms enrollment-based ones, and the optimal embedding depends on the input mixture.

This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers. Speaker embeddings are crucial not only for speaker recognition but also for various multi-speaker speech applications such as speaker diarization and target-speaker speech processing. Despite the challenges of obtaining a single speaker’s speech without pre-registration in multi-speaker scenarios, most studies on speaker embedding extraction focus on extracting embeddings only from single-speaker recordings. Some methods have been proposed for extracting speaker embeddings directly from multi-speaker recordings, but they typically require preparing a model for each possible number of speakers or involve complicated training procedures. The proposed method computes the embeddings of multiple speakers by focusing on different parts of the frame-wise embeddings extracted from the input multi-speaker audio. This is achieved by recursively computing attention weights for pooling the frame-wise embeddings. Additionally, we propose using the calculated attention weights to estimate the number of speakers in the recording, which allows the same model to be applied to various numbers of speakers. Experimental evaluations demonstrate the effectiveness of the proposed method in speaker verification and diarization tasks.

It is challenging to improve automatic speech recognition (ASR) performance in noisy conditions with a single-channel speech enhancement (SE) front-end. This is generally attributed to the processing distortions caused by the nonlinear processing of single-channel SE front-ends. However, the causes of such degraded ASR performance have not been fully investigated. How to design single-channel SE front-ends in a way that significantly improves ASR performance remains an open research question. In this study, we investigate a signal-level numerical metric that can explain the cause of degradation in ASR performance. To this end, we propose a novel analysis scheme based on the orthogonal projection-based decomposition of SE errors. This scheme manually modifies the ratio of the decomposed interference, noise, and artifact errors, and it enables us to directly evaluate the impact of each error type on ASR performance. Our analysis reveals the particularly detrimental effect of artifact errors on ASR performance compared to the other types of errors. This provides us with a more principled definition of processing distortions that cause the ASR performance degradation. Then, we study two practical approaches for reducing the impact of artifact errors. First, we prove that the simple observation adding (OA) post-processing (i.e., interpolating the enhanced and observed signals) can improve the signal-to-artifact ratio. Second, we propose a novel training objective, called artifact-boosted signal-to-distortion ratio (AB-SDR), which forces the model to estimate the enhanced signals with fewer artifact errors. Through experiments, we confirm that both the OA and AB-SDR approaches are effective in decreasing artifact errors caused by single-channel SE front-ends, allowing them to significantly improve ASR performance.

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.

We propose a new Customer Satisfaction Estimation (CSE) method that utilizes unsupervised representation learning. Though conventional methods have improved both the heuristic features and the estimation models, their performance is still insufficient as only small amounts of labeled training data can be expected. To mitigate this problem, the proposed method leverages a large amount of unlabeled data by unsupervised representation learning based on self-training. The key advance of the proposed method is to introduce a Multi-Format Prediction (MFP) loss to improve the performance of self-training for the inputs that contain both continuous and biased discrete features such as the number of occurrences of a particular word. MFP loss uses two loss functions based on regression and weighted binary classification to reconstruct both types of features with high accuracy. Experiments on real English contact center calls reveal the improved CSE performance attained by the proposed method.

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.

The combination of a deep neural network (DNN) -based speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end is a widely used approach to implement overlapping speech recognition. However, the SE front-end generates processing artifacts that can degrade the ASR performance. We previously found that such performance degradation can occur even under fully overlapping conditions, depending on the signal-to-interference ratio (SIR) and signal-to-noise ratio (SNR). To mitigate the degradation, we introduced a rule-based method to switch the ASR input between the enhanced and observed signals, which showed promising results. However, the rule’s optimality was unclear because it was heuristically designed and based only on SIR and SNR values. In this work, we propose a DNN-based switching method that directly estimates whether ASR will perform better on the enhanced or observed signals. We also introduce soft-switching that computes a weighted sum of the enhanced and observed signals for ASR input, with weights given by the switching model’s output posteriors. The proposed learning-based switching showed performance comparable to that of rule-based oracle switching. The soft-switching further improved the ASR performance and achieved a relative character error rate reduction of up to 23 % as compared with the conventional method.

It is challenging to improve automatic speech recognition (ASR) performance in noisy conditions with single-channel speech enhancement (SE).In this paper, we investigate the causes of ASR performance degradation by decomposing the SE errors using orthogonal projection-based decomposition (OPD).OPD decomposes the SE errors into noise and artifact components.The artifact component is defined as the SE error signal that cannot be represented as a linear combination of speech and noise sources.We propose manually scaling the error components to analyze their impact on ASR.We experimentally identify the artifact component as the main cause of performance degradation, and we find that mitigating the artifact can greatly improve ASR performance.Furthermore, we demonstrate that the simple observation adding (OA) technique (i.e., adding a scaled version of the observed signal to the enhanced speech) can monotonically increase the signal-to-artifact ratio under a mild condition.Accordingly, we experimentally confirm that OA improves ASR performance for both simulated and real recordings.The findings of this paper provide a better understanding of the influence of SE errors on ASR and open the door to future research on novel approaches for designing effective single-channel SE front-ends for ASR.

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 investigates the effectiveness and implementation of modality-specific large-scale pre-trained encoders for multimodal sentiment analysis (MSA). Although the effectiveness of pre-trained encoders in various fields has been reported, conventional MSA methods employ them for only linguistic modality, and their application has not been investigated. This paper compares the features yielded by large-scale pre-trained encoders with conventional heuristic features. One each of the largest pre-trained encoders publicly available for each modality are used; CLIP-ViT, WavLM, and BERT for visual, acoustic, and linguistic modalities, respectively. Experiments on two datasets reveal that methods with domain-specific pre-trained encoders attain better performance than those with conventional features in both unimodal and multimodal scenarios. We also find it better to use the outputs of the intermediate layers of the encoders than those of the output layer. The codes are available at https://github.com/ando-hub/MSA_Pretrain.

This paper presents a novel speech emotion recognition scheme that can deal with the individuality of emotion perception. Most conventional methods directly model the majority decision of multiple listener’s perceived emotions. However, emotion perception varies with the listener, which means the conventional methods can mismatch the recognition results to human perception. In order to mitigate this problem, we propose a Listener Adaptive (LA) model that reflects emotion recognition criteria of each listener. One-hot listener codes with several adaptation layers are employed in the LA model. The LA model yields the posterior probabilities of the listener-specific perceived emotions. Majority-voted emotion can be also estimated by averaging, in the LA model, the posterior probabilities for all listeners. Experiments on two emotional speech datasets demonstrate that the proposed approach offers improved listener-wise perceived emotion recognition performance in natural speech.

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.

Although recent advances in deep learning technology improved automatic speech recognition (ASR), it remains difficult to recognize speech when it overlaps other people's voices. Speech separation or extraction is often used as a front-end to ASR to handle such overlapping speech. However, deep neural network-based speech enhancement can generate `processing artifacts' as a side effect of the enhancement, which degrades ASR performance. For example, it is well known that single-channel noise reduction for non-speech noise (non-overlapping speech) often does not improve ASR. Likewise, the processing artifacts may also be detrimental to ASR in some conditions when processing overlapping speech with a separation/extraction method, although it is usually believed that separation/extraction improves ASR. In order to answer the question `Do we always have to separate/extract speech from mixtures?', we analyze ASR performance on observed and enhanced speech at various noise and interference conditions, and show that speech enhancement degrades ASR under some conditions even for overlapping speech. Based on these findings, we propose a simple switching algorithm between observed and enhanced speech based on the estimated signal-to-interference ratio and signal-to-noise ratio. We demonstrated experimentally that such a simple switching mechanism can improve recognition performance when processing artifacts are detrimental to ASR.

Target speaker extraction, which aims at extracting a target speaker's voice from a mixture of voices using audio, visual or locational clues, has received much interest. Recently an audio-visual target speaker extraction has been proposed that extracts target speech by using complementary audio and visual clues. Although audio-visual target speaker extraction offers a more stable performance than single modality methods for simulated data, its adaptation towards realistic situations has not been fully explored as well as evaluations on real recorded mixtures. One of the major issues to handle realistic situations is how to make the system robust to clue corruption because in real recordings both clues may not be equally reliable, e.g. visual clues may be affected by occlusions. In this work, we propose a novel attention mechanism for multi-modal fusion and its training methods that enable to effectively capture the reliability of the clues and weight the more reliable ones. Our proposals improve signal to distortion ratio (SDR) by 1.0 dB over conventional fusion mechanisms on simulated data. Moreover, we also record an audio-visual dataset of simultaneous speech with realistic visual clue corruption and show that audio-visual target speaker extraction with our proposals successfully work on real data.

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.

This paper proposes a latent statistical model for analyzing global positioning system (GPS) trajectory data. Because of the rapid spread of GPS-equipped devices, numerous GPS trajectories have become available, and they are useful for various location-aware systems. To better utilize GPS data, a number of sensor data mining techniques have been developed. This paper discusses the application of a latent statistical model to two closely related problems, namely, moving mode estimation and interpolation of the GPS observation. The proposed model estimates a latent mode of moving objects and represents moving patterns according to the mode by exploiting a large GPS trajectory dataset. We evaluate the effectiveness of the model through experiments using the GeoLife GPS Trajectories dataset and show that more than three-quarters of covered locations were correctly reproduced by interpolation at a fine granularity.

Participatory sensing produces incomplete sensor data. Thus, we have to fill in the gaps of any missing values in the sensor data in order to provide sensor-based services. We propose a method to estimate a missing value of incomplete sensor data. It accurately estimates a missing value by repeating two processes: selecting sensors locally correlated with the sensor that includes the missing value and then updating the training sensor dataset that consist of data from the selected sensors available for multiple regression. This procedure effectively helps to find more suitable neighbor records of a query record from the training sensor dataset and to refine the regression model using the records. It overcomes three problems that other estimation methods have: a decrease in the amount of available training sensor dataset due to missing values, the difficulty in finding similar records of a query due to the “curse of dimensionality,” and the complexity in formalizing the estimation model due to “overfitting.” The main feature of our method is the way it repeatedly prunes inessential sensors while exploiting the anti-monotone property in which the training sensor dataset R' that consist of the sensors V' ⊂ V is larger than the data R that consist of V. Empirical evaluations done using public datasets in which we appended missing values show that our method increases the training sensor dataset for estimation and improves estimation accuracy through repeated sensor selections. Furthermore, we confirmed through a field trial and a life-log enrichment trial, that our method was effective for estimating missing sensor values in a participatory sensing environment.

In this paper, we present a digital signal processor (DSP) implementation of real-time statistical voice conversion (VC) for silent speech enhancement and electrolaryngeal speech enhancement. As a silent speech interface, we focus on nonaudible murmur (NAM), which can be used in situations where audible speech is not acceptable. Electrolaryngeal speech is one of the typical types of alaryngeal speech produced by an alternative speaking method for laryngectomees. However, the sound quality of NAM and electrolaryngeal speech suffers from lack of naturalness. VC has proven to be one of the promising approaches to address this problem, and it has been successfully implemented on devices with sufficient computational resources. An implementation on devices that are highly portable but have limited computational resources would greatly contribute to its practical use. In this paper we further implement real-time VC on a DSP. To implement the two speech enhancement systems based on real-time VC, one from NAM to a whispered voice and the other from electrolaryngeal speech to a natural voice, we propose several methods for reducing computational cost while preserving conversion accuracy. We conduct experimental evaluations and show that real-time VC is capable of running on a DSP with little degradation. Index Terms: statistical voice conversion, real-time processing, reduction of computational cost, DSP, non-audible murmur, electrolaryngeal speech

We propose a method for improving motivation to participate in sensing services by presenting rankings in multidimensional hierarchical sets. We call this method Top of Worlds. Because previously proposed methods only rank a user among all other users, many have little chance of being ranked in the top group, resulting in little motivation to continue. Top of Worlds creates many sets with varying granularity to increase the chance of many users being ranked in the top group and presents these rankings in those sets. Through an experiment, we partially confirmed the validity of Top of Worlds.