Full-duplex dialogue audio, in which each speaker is recorded on a separate track, is an important resource for spoken dialogue research, but is difficult to collect at scale. Most in-the-wild two-speaker dialogue is available only as degraded monaural mixtures, making it unsuitable for systems requiring clean speaker-wise signals. We propose DialogueSidon, a model for joint restoration and separation of degraded monaural two-speaker dialogue audio. DialogueSidon combines a variational autoencoder (VAE) operates on the speech self-supervised learning (SSL) model feature, which compresses SSL model features into a compact latent space, with a diffusion-based latent predictor that recovers speaker-wise latent representations from the degraded mixture. Experiments on English, multilingual, and in-the-wild dialogue datasets show that DialogueSidon substantially improves intelligibility and separation quality over a baseline, while also achieving much faster inference.

For streaming speech recognition, a Transformerbased encoder has been widely used with block processing. Although many studies addressed improving emission latency of transducers, little work has been explored for improving encoding latency of the block processing. We seek to reduce latency by frequently emitting a chunk with a small shift rather than scarce large-chunk emissions, resulting in higher computational costs. To efficiently compute with the small chunk shift, we propose a new encoder, Spiralformer, tailored for block processing by combining layer dropping and early exiting. We skip layer computation in a cyclic manner and shift the computed layer in each block spirally, which completes computation for all the layers over the block processing. Experimentally, we observed that our method achieved 21.6% reduction in the averaged token emission delay in Librispeech, and 7.0% in CSJ, compared with the baseline with similar computational cost and word error rates.

In many real-world scenarios, such as meetings, multiple speakers are present with an unknown number of participants, and their utterances often overlap. We address these multi-speaker challenges by a novel attention-based encoder-decoder method augmented with special speaker class tokens obtained by speaker clustering. During inference, we select multiple recognition hypotheses conditioned on predicted speaker cluster tokens, and these hypotheses are merged by agglomerative hierarchical clustering (AHC) based on the normalized edit distance. The clustered hypotheses result in the multi-speaker transcriptions with the appropriate number of speakers determined by AHC. Our experiments on the LibriMix dataset demonstrate that our proposed method was particularly effective in complex 3-mix environments, achieving a 55% relative error reduction on clean data and a 36% relative error reduction on noisy data compared with conventional serialized output training.

Real-time speech enhancement (SE) is essential to online speech communication. Causal SE models use only the previous context while predicting future information, such as phoneme continuation, may help performing causal SE. The phonetic information is often represented by quantizing latent features of self-supervised learning (SSL) models. This work is the first to incorporate SSL features with causality into an SE model. The causal SSL features are encoded and combined with spectrogram features using feature-wise linear modulation to estimate a mask for enhancing the noisy input speech. Simultaneously, we quantize the causal SSL features using vector quantization to represent phonetic characteristics as semantic tokens. The model not only encodes SSL features but also predicts the future semantic tokens in multi-task learning (MTL). The experimental results using VoiceBank + DEMAND dataset show that our proposed method achieves 2.88 in PESQ, especially with semantic prediction MTL, in which we confirm that the semantic prediction played an important role in causal SE.

In speech recognition applications, it is important to recognize context-specific rare words, such as proper nouns. Tree-constrained Pointer Generator (TCPGen) has shown promise for this purpose, which efficiently biases such words with a prefix tree. While the original TCPGen relies on grapheme-based encoding, we propose extending it with phoneme-aware encoding to better recognize words of unusual pronunciations. As TCPGen handles biasing words as subword units, we propose obtaining subword-level phoneme-aware encoding by using alignment between phonemes and subwords. Furthermore, we propose injecting phoneme-level predictions from CTC into queries of TCPGen so that the model better interprets the phoneme-aware encodings. We conducted ASR experiments with TCPGen for RNN transducer. We observed that proposed phoneme-aware encoding outperformed ordinary grapheme-based encoding on both the English LibriSpeech and Japanese CSJ datasets, demonstrating the robustness of our approach across linguistically diverse languages.

Siddhant Arora, Hayato Futami, Jee-weon Jung, Yifan Peng, Roshan Sharma, Yosuke Kashiwagi, Emiru Tsunoo, Karen Livescu, Shinji Watanabe. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Most human interactions occur in the form of spoken conversations where the semantic meaning of a given utterance depends on the context. Each utterance in spoken conversation can be represented by many semantic and speaker attributes, and there has been an interest in building Spoken Language Understanding (SLU) systems for automatically predicting these attributes. Recent work has shown that incorporating dialogue history can help advance SLU performance. However, separate models are used for each SLU task, leading to an increase in inference time and computation cost. Motivated by this, we aim to ask: can we jointly model all the SLU tasks while incorporating context to facilitate low-latency and lightweight inference? To answer this, we propose a novel model architecture that learns dialog context to jointly predict the intent, dialog act, speaker role, and emotion for the spoken utterance. Note that our joint prediction is based on an autoregressive model and we need to decide the prediction order of dialog attributes, which is not trivial. To mitigate the issue, we also propose an order agnostic training method. Our experiments show that our joint model achieves similar results to task-specific classifiers and can effectively integrate dialog context to further improve the SLU performance.1

Recently there have been efforts to introduce new benchmark tasks for spoken language understanding (SLU), like semantic parsing. In this paper, we describe our proposed spoken semantic parsing system for the quality track (Track 1) in Spoken Language Understanding Grand Challenge which is part of ICASSP Signal Processing Grand Challenge 2023. We experiment with both end-to-end and pipeline systems for this task. Strong automatic speech recognition (ASR) models like Whisper and pretrained Language models (LM) like BART are utilized inside our SLU framework to boost performance. We also investigate the output level combination of various models to get an exact match accuracy of 80.8, which won the 1st place at the challenge.

This paper describes our system for the low-resource domain adaptation track (Track 3) in Spoken Language Understanding Grand Challenge, which is a part of ICASSP Signal Processing Grand Challenge 2023. In the track, we adopt a pipeline approach of ASR and NLU. For ASR, we fine-tune Whisper for each domain with upsampling. For NLU, we fine-tune BART on all the Track3 data and then on low-resource domain data. We apply masked LM (MLM) -based data augmentation, where some of input tokens and corresponding target labels are replaced using MLM. We also apply a retrieval-based approach, where model input is augmented with similar training samples. As a result, we achieved exact match (EM) accuracy 63.3/75.0 (average: 69.15) for reminder/weather domain, and won the 1st place at the challenge.

Disfluency detection has mainly been solved in a pipeline approach, as post-processing of speech recognition. In this study, we propose Transformer-based encoder-decoder models that jointly solve speech recognition and disfluency detection, which work in a streaming manner. Compared to pipeline approaches, the joint models can leverage acoustic information that makes disfluency detection robust to recognition errors and provide non-verbal clues. Moreover, joint modeling results in low-latency and lightweight inference. We investigate two joint model variants for streaming disfluency detection: a transcript-enriched model and a multi-task model. The transcript- enriched model is trained on text with special tags indicating the starting and ending points of the disfluent part. However, it has problems with latency and standard language model adaptation, which arise from the additional disfluency tags. We propose a multi-task model to solve such problems, which has two output layers at the Transformer decoder; one for speech recognition and the other for disfluency detection. It is modeled to be conditioned on the currently recognized token with an additional token-dependency mechanism. We show that the proposed joint models outperformed a BERT-based pipeline approach in both accuracy and latency, on both the Switch- board and the corpus of spontaneous Japanese.

In this paper, we report our team’s study on track 2 of the Spoken Language Understanding Grand Challenge, which is a component of the ICASSP Signal Processing Grand Challenge 2023. The task is intended for on-device processing and involves estimating semantic parse labels from speech using a model with 15 million parameters. We use E2E E-Branchformer-based spoken language understanding model, which is more parameter controllable than cascade models, and reduced the parameter size through sequential distillation and tensor decomposition techniques. On the STOP dataset, we achieved an exact match accuracy of 70.9% under the tight constraint of 15 million parameters.

Although end-to-end text-to-speech (TTS) models can generate natural speech, challenges still remain when it comes to estimating sentence-level phonetic and prosodic information from raw text in Japanese TTS systems. In this paper, we propose a method for polyphone disambiguation (PD) and accent prediction (AP). The proposed method incorporates explicit features extracted from morphological analysis and implicit features extracted from pre-trained language models (PLMs). We use BERT and Flair embeddings as implicit features and examine how to combine them with explicit features. Our objective evaluation results showed that the proposed method improved the accuracy by 5.7 points in PD and 6.0 points in AP. Moreover, the perceptual listening test results confirmed that a TTS system employing our proposed model as a front-end achieved a mean opinion score close to that of synthesized speech with ground-truth pronunciation and accent in terms of naturalness.

Recording and annotating real sound events for a sound event localization and detection (SELD) task is time consuming, and data augmentation techniques are often favored when the amount of data is limited. However, how to augment the spatial information in a dataset, including unlabeled directional interference events, remains an open research question. Furthermore, directional interference events make it difficult to accurately extract spatial characteristics from target sound events. To address this problem, we propose an impulse response simulation framework (IRS) that augments spatial characteristics using simulated room impulse responses (RIR). RIRs corresponding to a microphone array assumed to be placed in various rooms are accurately simulated, and the source signals of the target sound events are extracted from a mixture. The simulated RIRs are then convolved with the extracted source signals to obtain an augmented multi-channel training dataset. Evaluation results obtained using the TAU-NIGENS Spatial Sound Events 2021 dataset show that the IRS contributes to improving the overall SELD performance. Additionally, we conducted an ablation study to discuss the contribution and need for each component within the IRS.

Speech samples recorded in both indoor and outdoor environments are often contaminated with secondary audio sources. Most end-to-end monaural speech recognition systems either remove these background sounds using speech enhancement or train noise-robust models. For better model interpretability and holistic understanding, we aim to bring together the growing field of automated audio captioning (AAC) and the thoroughly studied automatic speech recognition (ASR). The goal of AAC is to generate natural language descriptions of contents in audio samples. We propose several approaches for end-to-end joint modeling of ASR and AAC tasks and demonstrate their advantages over traditional approaches, which model these tasks independently. A major hurdle in evaluating our proposed approach is the lack of labeled audio datasets with both speech transcriptions and audio captions. Therefore we also create a multi-task dataset by mixing the clean speech Wall Street Journal corpus with multiple levels of background noises chosen from the AudioCaps dataset. We also perform extensive experimental evaluation and show improvements of our proposed methods as compared to existing state-of-the-art ASR and AAC methods.

Sound event localization and detection (SELD) involves identifying the direction-of-arrival (DOA) and the event class. The SELD methods with a class-wise output format make the model predict activities of all sound event classes and corresponding locations. The class-wise methods can output activity-coupled Cartesian DOA (ACCDOA) vectors, which enable us to solve a SELD task with a single target using a single network. However, there is still a challenge in detecting the same event class from multiple locations. To overcome this problem while maintaining the advantages of the class-wise format, we extended ACCDOA to a multi one and proposed auxiliary duplicating permutation invariant training (ADPIT). The multi-ACCDOA format (a class- and track-wise output format) enables the model to solve the cases with overlaps from the same class. The class-wise ADPIT scheme enables each track of the multi-ACCDOA format to learn with the same target as the single-ACCDOA format. In evaluations with the DCASE 2021 Task 3 dataset, the model trained with the multi-ACCDOA format and with the class-wise ADPIT detects overlapping events from the same class while maintaining its performance in the other cases. Also, the proposed method performed comparably to state-of-the-art SELD methods with fewer parameters.

A streaming style inference of encoder–decoder automatic speech recognition (ASR) systems is important for reducing latency, which is essential for interactive use cases. To this end, we propose a novel blockwise synchronous decoding algorithm with a hybrid approach that combines endpoint prediction and endpoint post-determination. In the endpoint prediction, we compute the expectation of the number of tokens that are yet to be emitted in the encoder features of the current blocks using the CTC posterior. Based on the expectation value, the decoder predicts the endpoint to realize continuous block synchronization, as a running stitch. Meanwhile, end-point post-determination probabilistically detects backward jump of the source–target attention, which is caused by the misprediction of endpoints. Then it resumes decoding by discarding those hypotheses, as back stitch. We combine these methods into a hybrid approach, namely run-and-back stitch search, which reduces the computational cost and latency. Evaluations of various ASR tasks show the efficiency of our proposed decoding algorithm, which achieves a latency reduction, for instance in the Librispeech test set from 1487 ms to 821 ms at the 90th percentile, while maintaining a high recognition accuracy.

End-to-end automatic speech recognition suffers from adaptation to unknown target domain speech despite being trained with a large amount of paired audio-text data.Recent studies estimate a linguistic bias of the model as the internal language model (LM).To effectively adapt to the target domain, the internal LM is subtracted from the posterior during inference and fused with an external target-domain LM.However, this fusion complicates the inference and the estimation of the internal LM may not always be accurate.In this paper, we propose a simple external LM fusion method for domain adaptation, which considers the internal LM estimation in its training.We directly model the residual factor of the external and internal LMs, namely the residual LM.To stably train the residual LM, we propose smoothing the estimated internal LM and optimizing it with a combination of cross-entropy and mean-squared-error losses, which consider the statistical behaviors of the internal LM in the target domain data.We experimentally confirmed that the proposed residual LM performs better than the internal LM estimation in most of the cross-domain and intra-domain scenarios.

In punctuation restoration, we try to recover the missing punctuation from automatic speech recognition output to improve understandability. Currently, large pre-trained transformers such as BERT set the benchmark on this task but there are two main drawbacks to these models. First, the pre-training data does not match the output data from speech recognition that contains errors. Second, the large number of model parameters increases inference time. To address the former, we use a multi-task learning framework with ELECTRA, a recently proposed improvement on BERT, that has a generator-discriminator structure. The generator allows us to inject errors into the training data and, as our experiments show, this improves robustness against speech recognition errors during inference. To address the latter, we investigate knowledge distillation and parameter pruning of ELECTRA. In our experiments on the IWSLT 2012 benchmark data, a model with less than 11% the size of BERT achieved better performance while having an 82% faster inference time.

ISelf-attention (SA) based models have recently achieved significant performance improvements in hybrid and end-to-end automatic speech recognition (ASR) systems owing to their flexible context modeling capability. However, it is also known that the accuracy degrades when applying SA to long sequence data. This is mainly due to the length mismatch between the inference and training data because the training data are usually divided into short segments for efficient training. To mitigate this mismatch, we propose a new architecture, which is a variant of the Gaussian kernel, which itself is a shift-invariant kernel. First, we mathematically demonstrate that self-attention with shared weight parameters for queries and keys is equivalent to a normalized kernel function. By replacing this kernel function with the proposed Gaussian kernel, the architecture becomes completely shift-invariant with the relative position information embedded using a frame indexing technique. The proposed Gaussian kernelized SA was applied to connectionist temporal classification (CTC) based ASR. An experimental evaluation with the Corpus of Spontaneous Japanese (CSJ) and TEDLIUM 3 benchmarks shows that the proposed SA achieves a significant improvement in accuracy (e.g., from 24.0% WER to 6.0% in CSJ) in long sequence data without any windowing techniques.

Although end-to-end automatic speech recognition (E2E ASR) has achieved great performance in tasks that have numerous paired data, it is still challenging to make E2E ASR robust against noisy and low-resource conditions.In this study, we investigated data augmentation methods for E2E ASR in distanttalk scenarios.E2E ASR models are trained on the series of CHiME challenge datasets, which are suitable tasks for studying robustness against noisy and spontaneous speech.We propose to use three augmentation methods and thier combinations: 1) data augmentation using text-to-speech (TTS) data, 2) cycleconsistent generative adversarial network (Cycle-GAN) augmentation trained to map two different audio characteristics, the one of clean speech and of noisy recordings, to match the testing condition, and 3) pseudo-label augmentation provided by the pretrained ASR module for smoothing label distributions.Experimental results using the CHiME-6/CHiME-4 datasets show that each augmentation method individually improves the accuracy on top of the conventional SpecAugment; further improvements are obtained by combining these approaches.We achieved 4.3% word error rate (WER) reduction, which was more significant than that of the SpecAugment, when we combine all three augmentations for the CHiME-6 task.

The Transformer self-attention network has shown promising performance as an alternative to recurrent neural networks in end-to-end (E2E) automatic speech recognition (ASR) systems. However, Transformer has a drawback in that the entire input sequence is required to compute both self-attention and source-target attention. In this paper, we propose a novel blockwise synchronous beam search algorithm based on blockwise processing of encoder to perform streaming E2E Transformer ASR. In the beam search, encoded feature blocks are synchronously aligned using a block boundary detection technique, where a reliability score of each predicted hypothesis is evaluated based on the end-of-sequence and repeated tokens in the hypothesis. Evaluations of the HKUST and AISHELL-1 Mandarin, LibriSpeech English, and CSJ Japanese tasks show that the proposed streaming Transformer algorithm outperforms conventional online approaches, including monotonic chunkwise attention (MoChA), especially when using the knowledge distillation technique. An ablation study indicates that our streaming approach contributes to reducing the response time, and the repetition criterion contributes significantly in certain tasks. Our streaming ASR models achieve comparable or superior performance to batch models and other streaming-based Transformer methods in all tasks considered.

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks (RNNs) in end-to-end (E2E) automatic speech recognition (ASR) systems. However, the Transformer has a drawback in that the entire input sequence is required to compute self-attention. In this paper, we propose a new block processing method for the Transformer encoder by introducing a context-aware inheritance mechanism. An additional context embedding vector handed over from the previously processed block helps to encode not only local acoustic information but also global linguistic, channel, and speaker attributes. We introduce a novel mask technique to implement the context inheritance to train the model efficiently. Evaluations of the Wall Street Journal (WSJ), Librispeech, VoxForge Italian, and AISHELL-1 Mandarin speech recognition datasets show that our proposed contextual block processing method outperforms naive block processing consistently. Furthermore, the attention weight tendency of each layer is analyzed to clarify how the added contextual inheritance mechanism models the global information.

An on-device DNN-HMM speech recognition system efficiently works with a limited vocabulary in the presence of a variety of predictable noise. In such a case, vocabulary and environment adaptation is highly effective. In this paper, we propose a novel method of end-to-end (E2E) adaptation, which adjusts not only an acoustic model (AM) but also a weighted finite-state transducer (WFST). We convert a pretrained WFST to a trainable neural network and adapt the system to target environments/vocabulary by E2E joint training with an AM. We replicate Viterbi decoding with forward--backward neural network computation, which is similar to recurrent neural networks (RNNs). By pooling output score sequences, a vocabulary posterior for each utterance is obtained and used for discriminative loss computation. Experiments using 2--10 hours of English/Japanese adaptation datasets indicate that the fine-tuning of only WFSTs and that of only AMs are both comparable to a state-of-the-art adaptation method, and E2E joint training of the two components achieves the best recognition performance. We also adapt each language system to the other language using the adaptation data, and the results show that the proposed method also works well for language adaptations.

A broadcast news stream consists of a number of stories and it is an important task to find the boundaries of stories automatically in news analysis. We capture the topic structure using a hierarchical model based on a Recurrent Neural Network (RNN) sentence modeling layer and a bidirectional Long Short-Term Memory (LSTM) topic modeling layer, with a fusion of acoustic and lexical features. Both features are accumulated with RNNs and trained jointly within the model to be fused at the sentence level. We conduct experiments on the topic detection and tracking (TDT4) task comparing combinations of two modalities trained with limited amount of parallel data. Further we utilize additional sufficient text data for training to polish our model. Experimental results indicate that the hierarchical RNN topic modeling takes advantage of the fusion scheme, especially with additional text training data, with a higher F1-measure compared to conventional state-of-the-art methods.

A broadcast news stream consists of a number of stories and each story consists of several sentences. We capture this structure using a hierarchical model based on a word-level Recurrent Neural Network (RNN) sentence modeling layer and a sentence-level bidirectional Long Short-Term Memory (LSTM) topic modeling layer. First, the word-level RNN layer extracts a vector embedding the sentence information from the given transcribed lexical tokens of each sentence. These sentence embedding vectors are fed into a bidirectional LSTM that models the sentence and topic transitions. A topic posterior for each sentence is estimated discriminatively and a Hidden Markov model (HMM) follows to decode the story sequence and identify story boundaries. Experiments on the topic detection and tracking (TDT2) task indicate that the hierarchical RNN topic modeling achieves the best story segmentation performance with a higher F1-measure compared to conventional state-of-the-art methods. We also compare variations of our model to infer the optimal structure for the story segmentation task.

This paper discusses a new approach for clustering sequences of bar-long percussive and bass-line patterns in audio music collections and its application to genre classification. Many musical genres and styles are characterized by two kinds of distinct representative patterns, i.e., percussive patterns and bass-line patterns. So far, in most automatic genre classification systems, rhythmic and bass melody information has not been effectively used. In order to extract bar-long unit rhythmic patterns for a music collection, we propose a clustering method based on one-pass dynamic programming andk-means clustering. For clustering bass-line patterns, a method based onk-means clustering capable of handling pitch-shifting is proposed. After extracting these two fundamental kinds of patterns for each style/genre, feature vectors which are suitable for representing information about the patterns are proposed for supervised learning. Experimental results show that the automatically calculated rhythmic pattern information and bass pattern information can be used to effectively classify musical genre/style and improve upon current approaches based on timbral features.

This paper discusses an approach for the feature extraction for audio mood classification which is an important and tough problem in the field of music information retrieval (MIR). In this task the timbral information has been widely used, however many musical moods are characterized not only by timbral information but also by musical scale and temporal features such as rhythm patterns and bass-line patterns. In particular, modern music pieces mostly have certain fixed rhythm and bass-line patterns, and these patterns can characterize the impression of songs. We have proposed the extraction of rhythm and bass-line patterns, and these unit pattern analysis are combined with statistical feature extraction for mood classification. Experimental results show that the automatically calculated unit pattern information can be used to effectively classify musical mood.

This paper discusses an approach to extract constituent percussive bar-long patterns in a music piece given as acoustic signal and to analyze the music structure with a map of constituent rhythmic patterns. Possible applications include music genre classification, music information retrieval (MIR) and music modification such as replacing rhythmic patterns with others. We propose a mathematical method based on One-pass DP algorithm and k-means clustering to extract unit percussive rhythmic patterns. As the result of identifying and localization the unit patterns in the entire piece, we obtained a music structure in the form of a map of rhythmic patterns.

Many musical genres and styles are characterized by distinct representative rhythmic patterns. In most automatic genre classification systems global statistical features based on timbral dynamics such as mel-frequency cepstral coefficients (MFCC) are utilized but so far rhythmic information has not so effectively been used. In order to extract bar-long unit rhythmic patterns for a music collection we propose a clustering method based on one-pass dynamic programming and k-means clustering. After extracting the fundamental rhythmic patterns for each style/genre a pattern occurrence histogram is calculated and used as a feature vector for supervised learning. Experimental results show that the automatically calculated rhythmic pattern information can be used to effectively classify musical genre/style and improve upon current approaches based on timbral features.