Related papers: Layer-wise Analysis of a Self-supervised Speech Re…

Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…

Significant strides have been made in creating voice identity representations using speech data. However, the same level of progress has not been achieved for singing voices. To bridge this gap, we suggest a framework for training singer…

Previous work has shown that for low-resource source languages, automatic speech-to-text translation (AST) can be improved by pretraining an end-to-end model on automatic speech recognition (ASR) data from a high-resource language. However,…

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…

Model architectures such as wav2vec 2.0 and HuBERT have been proposed to learn speech representations from audio waveforms in a self-supervised manner. When they are combined with downstream tasks such as keyword spotting and speaker…

We employ a combination of recent developments in semi-supervised learning for automatic speech recognition to obtain state-of-the-art results on LibriSpeech utilizing the unlabeled audio of the Libri-Light dataset. More precisely, we carry…

Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain…

Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in…

Recently, self-supervised pre-training has shown significant improvements in many areas of machine learning, including speech and NLP. We propose using large self-supervised pre-trained models for both audio and text modality with…

In this paper, we propose a language-universal adapter learning framework based on a pre-trained model for end-to-end multilingual automatic speech recognition (ASR). For acoustic modeling, the wav2vec 2.0 pre-trained model is fine-tuned by…

Recently, self-supervised pre-training has gained success in automatic speech recognition (ASR). However, considering the difference between speech accents in real scenarios, how to identify accents and use accent features to improve ASR is…

A deep Transformer model with good evaluation score does not mean each subnetwork (a.k.a transformer block) learns reasonable representation. Diagnosing abnormal representation and avoiding it can contribute to achieving a better evaluation…

We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream…

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Collecting speech data is an important step in training speech recognition systems and other speech-based machine learning models. However, the issue of privacy protection is an increasing concern that must be addressed. The current study…

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Although automatic speech recognition (ASR) can perform well in common non-overlapping environments, sustaining performance in multi-talker overlapping speech recognition remains challenging. Recent research revealed that ASR model's…

Automatic assessment of dysarthric speech is essential for sustained treatments and rehabilitation. However, obtaining atypical speech is challenging, often leading to data scarcity issues. To tackle the problem, we propose a novel…