arXiv subjects

Shinji Watanabe

Publications and source records attributed to Shinji Watanabe.

At least 271 records · Page 15Linked to original sources

arXiv2023

EURO: ESPnet Unsupervised ASR Open-source Toolkit

This paper describes the ESPnet Unsupervised ASR Open-source Toolkit (EURO), an end-to-end open-source toolkit for unsupervised automatic speech recognition (UASR). EURO adopts the state-of-the-art UASR learning method introduced by the Wav2vec-U, originally implemented at FAIRSEQ, which leverages self-supervised speech representations and adversarial training. In addition to wav2vec2, EURO extends the functionality and promotes reproducibility for UASR tasks by integrating S3PRL and k2, resulting in flexible frontends from 27 self-supervised models and various graph-based decoding strategies. EURO is implemented in ESPnet and follows its unified pipeline to provide UASR recipes with a complete setup. This improves the pipeline's efficiency and allows EURO to be easily applied to existing datasets in ESPnet. Extensive experiments on three mainstream self-supervised models demonstrate the toolkit's effectiveness and achieve state-of-the-art UASR performance on TIMIT and LibriSpeech datasets. EURO will be publicly available at https://github.com/espnet/espnet, aiming to promote this exciting and emerging research area based on UASR through open-source activity.

cs.CL↗

arXiv2023

A New Benchmark of Aphasia Speech Recognition and Detection Based on E-Branchformer and Multi-task Learning

Aphasia is a language disorder that affects the speaking ability of millions of patients. This paper presents a new benchmark for Aphasia speech recognition and detection tasks using state-of-the-art speech recognition techniques with the AphsiaBank dataset. Specifically, we introduce two multi-task learning methods based on the CTC/Attention architecture to perform both tasks simultaneously. Our system achieves state-of-the-art speaker-level detection accuracy (97.3%), and a relative WER reduction of 11% for moderate Aphasia patients. In addition, we demonstrate the generalizability of our approach by applying it to another disordered speech database, the DementiaBank Pitt corpus. We will make our all-in-one recipes and pre-trained model publicly available to facilitate reproducibility. Our standardized data preprocessing pipeline and open-source recipes enable researchers to compare results directly, promoting progress in disordered speech processing.

eess.AS↗

arXiv2023

A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks

Conformer, a convolution-augmented Transformer variant, has become the de facto encoder architecture for speech processing due to its superior performance in various tasks, including automatic speech recognition (ASR), speech translation (ST) and spoken language understanding (SLU). Recently, a new encoder called E-Branchformer has outperformed Conformer in the LibriSpeech ASR benchmark, making it promising for more general speech applications. This work compares E-Branchformer and Conformer through extensive experiments using different types of end-to-end sequence-to-sequence models. Results demonstrate that E-Branchformer achieves comparable or better performance than Conformer in almost all evaluation sets across 15 ASR, 2 ST, and 3 SLU benchmarks, while being more stable during training. We will release our training configurations and pre-trained models for reproducibility, which can benefit the speech community.

cs.CL↗

arXiv2023

Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation

Most of the speech translation models heavily rely on parallel data, which is hard to collect especially for low-resource languages. To tackle this issue, we propose to build a cascaded speech translation system without leveraging any kind of paired data. We use fully unpaired data to train our unsupervised systems and evaluate our results on CoVoST 2 and CVSS. The results show that our work is comparable with some other early supervised methods in some language pairs. While cascaded systems always suffer from severe error propagation problems, we proposed denoising back-translation (DBT), a novel approach to building robust unsupervised neural machine translation (UNMT). DBT successfully increases the BLEU score by 0.7--0.9 in all three translation directions. Moreover, we simplified the pipeline of our cascaded system to reduce inference latency and conducted a comprehensive analysis of every part of our work. We also demonstrate our unsupervised speech translation results on the established website.

cs.CL↗

arXiv2023

Streaming Joint Speech Recognition and Disfluency Detection

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 Switchboard and the corpus of spontaneous Japanese.

cs.CL↗

arXiv2023

The Pipeline System of ASR and NLU with MLM-based Data Augmentation toward STOP Low-resource 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.

cs.CL↗

arXiv2023

A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing toward STOP Quality Challenge

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.

cs.CL↗

arXiv2023

Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History

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.

cs.CL↗

arXiv2023

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

Large language models (LLMs) have exhibited remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. Despite the recent success, current LLMs are not capable of processing complex audio information or conducting spoken conversations (like Siri or Alexa). In this work, we propose a multi-modal AI system named AudioGPT, which complements LLMs (i.e., ChatGPT) with 1) foundation models to process complex audio information and solve numerous understanding and generation tasks; and 2) the input/output interface (ASR, TTS) to support spoken dialogue. With an increasing demand to evaluate multi-modal LLMs of human intention understanding and cooperation with foundation models, we outline the principles and processes and test AudioGPT in terms of consistency, capability, and robustness. Experimental results demonstrate the capabilities of AudioGPT in solving AI tasks with speech, music, sound, and talking head understanding and generation in multi-round dialogues, which empower humans to create rich and diverse audio content with unprecedented ease. Our system is publicly available at \url{https://github.com/AIGC-Audio/AudioGPT}.

cs.CL↗

arXiv2023

BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model

This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the conditional independence assumptions used in conventional CTC and incorporates linguistic knowledge through the explicit output dependency obtained by BERT contextual embedding. BERT-CTC attends to the full contexts of the input and hypothesized output sequences via the self-attention mechanism. This mechanism encourages a model to learn inner/inter-dependencies between the audio and token representations while maintaining CTC's training efficiency. During inference, BERT-CTC combines a mask-predict algorithm with CTC decoding, which iteratively refines an output sequence. The experimental results reveal that BERT-CTC improves over conventional approaches across variations in speaking styles and languages. Finally, we show that the semantic representations in BERT-CTC are beneficial towards downstream spoken language understanding tasks.

eess.AS↗

arXiv2023

Neural Speech Enhancement with Very Low Algorithmic Latency and Complexity via Integrated Full- and Sub-Band Modeling

We propose FSB-LSTM, a novel long short-term memory (LSTM) based architecture that integrates full- and sub-band (FSB) modeling, for single- and multi-channel speech enhancement in the short-time Fourier transform (STFT) domain. The model maintains an information highway to flow an over-complete input representation through multiple FSB-LSTM modules. Each FSB-LSTM module consists of a full-band block to model spectro-temporal patterns at all frequencies and a sub-band block to model patterns within each sub-band, where each of the two blocks takes a down-sampled representation as input and returns an up-sampled discriminative representation to be added to the block input via a residual connection. The model is designed to have a low algorithmic complexity, a small run-time buffer and a very low algorithmic latency, at the same time producing a strong enhancement performance on a noisy-reverberant speech enhancement task even if the hop size is as low as $2$ ms.

eess.AS↗

arXiv2023

Enhancing Speech-to-Speech Translation with Multiple TTS Targets

It has been known that direct speech-to-speech translation (S2ST) models usually suffer from the data scarcity issue because of the limited existing parallel materials for both source and target speech. Therefore to train a direct S2ST system, previous works usually utilize text-to-speech (TTS) systems to generate samples in the target language by augmenting the data from speech-to-text translation (S2TT). However, there is a limited investigation into how the synthesized target speech would affect the S2ST models. In this work, we analyze the effect of changing synthesized target speech for direct S2ST models. We find that simply combining the target speech from different TTS systems can potentially improve the S2ST performances. Following that, we also propose a multi-task framework that jointly optimizes the S2ST system with multiple targets from different TTS systems. Extensive experiments demonstrate that our proposed framework achieves consistent improvements (2.8 BLEU) over the baselines on the Fisher Spanish-English dataset.

cs.SD↗

arXiv2023

Context-aware Fine-tuning of Self-supervised Speech Models

Self-supervised pre-trained transformers have improved the state of the art on a variety of speech tasks. Due to the quadratic time and space complexity of self-attention, they usually operate at the level of relatively short (e.g., utterance) segments. In this paper, we study the use of context, i.e., surrounding segments, during fine-tuning and propose a new approach called context-aware fine-tuning. We attach a context module on top of the last layer of a pre-trained model to encode the whole segment into a context embedding vector which is then used as an additional feature for the final prediction. During the fine-tuning stage, we introduce an auxiliary loss that encourages this context embedding vector to be similar to context vectors of surrounding segments. This allows the model to make predictions without access to these surrounding segments at inference time and requires only a tiny overhead compared to standard fine-tuned models. We evaluate the proposed approach using the SLUE and Libri-light benchmarks for several downstream tasks: Automatic speech recognition (ASR), named entity recognition (NER), and sentiment analysis (SA). The results show that context-aware fine-tuning not only outperforms a standard fine-tuning baseline but also rivals a strong context injection baseline that uses neighboring speech segments during inference.

eess.AS↗

arXiv2023

BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder

We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic speech recognition (E2E-ASR) model formulated by the transducer with a BERT-enhanced encoder. Integrating a large-scale pre-trained language model (LM) into E2E-ASR has been actively studied, aiming to utilize versatile linguistic knowledge for generating accurate text. One crucial factor that makes this integration challenging lies in the vocabulary mismatch; the vocabulary constructed for a pre-trained LM is generally too large for E2E-ASR training and is likely to have a mismatch against a target ASR domain. To overcome such an issue, we propose BECTRA, an extended version of our previous BERT-CTC, that realizes BERT-based E2E-ASR using a vocabulary of interest. BECTRA is a transducer-based model, which adopts BERT-CTC for its encoder and trains an ASR-specific decoder using a vocabulary suitable for a target task. With the combination of the transducer and BERT-CTC, we also propose a novel inference algorithm for taking advantage of both autoregressive and non-autoregressive decoding. Experimental results on several ASR tasks, varying in amounts of data, speaking styles, and languages, demonstrate that BECTRA outperforms BERT-CTC by effectively dealing with the vocabulary mismatch while exploiting BERT knowledge.

eess.AS↗

arXiv2023

InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss

This paper presents InterMPL, a semi-supervised learning method of end-to-end automatic speech recognition (ASR) that performs pseudo-labeling (PL) with intermediate supervision. Momentum PL (MPL) trains a connectionist temporal classification (CTC)-based model on unlabeled data by continuously generating pseudo-labels on the fly and improving their quality. In contrast to autoregressive formulations, such as the attention-based encoder-decoder and transducer, CTC is well suited for MPL, or PL-based semi-supervised ASR in general, owing to its simple/fast inference algorithm and robustness against generating collapsed labels. However, CTC generally yields inferior performance than the autoregressive models due to the conditional independence assumption, thereby limiting the performance of MPL. We propose to enhance MPL by introducing intermediate loss, inspired by the recent advances in CTC-based modeling. Specifically, we focus on self-conditional and hierarchical conditional CTC, that apply auxiliary CTC losses to intermediate layers such that the conditional independence assumption is explicitly relaxed. We also explore how pseudo-labels should be generated and used as supervision for intermediate losses. Experimental results in different semi-supervised settings demonstrate that the proposed approach outperforms MPL and improves an ASR model by up to a 12.1% absolute performance gain. In addition, our detailed analysis validates the importance of the intermediate loss.

eess.AS↗

arXiv2023

TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation

We propose TF-GridNet, a novel multi-path deep neural network (DNN) operating in the time-frequency (T-F) domain, for monaural talker-independent speaker separation in anechoic conditions. The model stacks several multi-path blocks, each consisting of an intra-frame spectral module, a sub-band temporal module, and a full-band self-attention module, to leverage local and global spectro-temporal information for separation. The model is trained to perform complex spectral mapping, where the real and imaginary (RI) components of the input mixture are stacked as input features to predict target RI components. Besides using the scale-invariant signal-to-distortion ratio (SI-SDR) loss for model training, we include a novel loss term to encourage separated sources to add up to the input mixture. Without using dynamic mixing, we obtain 23.4 dB SI-SDR improvement (SI-SDRi) on the WSJ0-2mix dataset, outperforming the previous best by a large margin.

cs.SD↗

arXiv2023

I3D: Transformer architectures with input-dependent dynamic depth for speech recognition

Transformer-based end-to-end speech recognition has achieved great success. However, the large footprint and computational overhead make it difficult to deploy these models in some real-world applications. Model compression techniques can reduce the model size and speed up inference, but the compressed model has a fixed architecture which might be suboptimal. We propose a novel Transformer encoder with Input-Dependent Dynamic Depth (I3D) to achieve strong performance-efficiency trade-offs. With a similar number of layers at inference time, I3D-based models outperform the vanilla Transformer and the static pruned model via iterative layer pruning. We also present interesting analysis on the gate probabilities and the input-dependency, which helps us better understand deep encoders.

cs.CL↗

arXiv2023

The Multimodal Information based Speech Processing (MISP) 2022 Challenge: Audio-Visual Diarization and Recognition

The Multi-modal Information based Speech Processing (MISP) challenge aims to extend the application of signal processing technology in specific scenarios by promoting the research into wake-up words, speaker diarization, speech recognition, and other technologies. The MISP2022 challenge has two tracks: 1) audio-visual speaker diarization (AVSD), aiming to solve ``who spoken when'' using both audio and visual data; 2) a novel audio-visual diarization and recognition (AVDR) task that focuses on addressing ``who spoken what when'' with audio-visual speaker diarization results. Both tracks focus on the Chinese language, and use far-field audio and video in real home-tv scenarios: 2-6 people communicating each other with TV noise in the background. This paper introduces the dataset, track settings, and baselines of the MISP2022 challenge. Our analyses of experiments and examples indicate the good performance of AVDR baseline system, and the potential difficulties in this challenge due to, e.g., the far-field video quality, the presence of TV noise in the background, and the indistinguishable speakers.

cs.MM↗