Related papers: Semi-supervised Sequence-to-sequence ASR using Unp…

For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition…

Self-supervised learning of speech representations has achieved impressive results in improving automatic speech recognition (ASR). In this paper, we show that data selection is important for self-supervised learning. We propose a simple…

Speech enhancement has recently achieved great success with various deep learning methods. However, most conventional speech enhancement systems are trained with supervised methods that impose two significant challenges. First, a majority…

Continual learning for automatic speech recognition (ASR) systems poses a challenge, especially with the need to avoid catastrophic forgetting while maintaining performance on previously learned tasks. This paper introduces a novel approach…

Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries. Although the constituent…

Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world's languages do not have usable systems due to the lack of large speech datasets to train these models.…

This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages. Two approaches are considered. The first constructs four separate bilingual…

Recent work in the field of speech enhancement (SE) has involved the use of self-supervised speech representations (SSSRs) as feature transformations in loss functions. However, in prior work, very little attention has been paid to the…

Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabeled speech, which is…

With the surge of online meetings, it has become more critical than ever to provide high-quality speech audio and live captioning under various noise conditions. However, most monaural speech enhancement (SE) models introduce processing…

Self-supervised learning (SSL) has transformed speech processing, yet its reliance on massive pre-training datasets remains a bottleneck. While robustness is often attributed to scale and diversity, the role of the data distribution is less…

To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and…

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial…

Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system…

Recent research has shown that attention-based sequence-to-sequence models such as Listen, Attend, and Spell (LAS) yield comparable results to state-of-the-art ASR systems on various tasks. In this paper, we describe the development of such…

We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort to employ ASR-based keyword spotting systems to support…

In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian…

Inverse text normalization (ITN) is crucial for converting spoken-form into written-form, especially in the context of automatic speech recognition (ASR). While most downstream tasks of ASR rely on written-form, ASR systems often output…

This paper presents a novel data augmentation technique for text-to-speech (TTS), that allows to generate new (text, audio) training examples without requiring any additional data. Our goal is to increase diversity of text conditionings…

Multilingual end-to-end models have shown great improvement over monolingual systems. With the development of pre-training methods on speech, self-supervised multilingual speech representation learning like XLSR has shown success in…