Related papers: A Further Study of Unsupervised Pre-training for T…

Speech recognition technologies are gaining enormous popularity in various industrial applications. However, building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To…

Recent developments in pre-trained speech representation utilizing self-supervised learning (SSL) have yielded exceptional results on a variety of downstream tasks. One such technique, known as masked predictive coding (MPC), has been…

Self-supervised learning via masked prediction pre-training (MPPT) has shown impressive performance on a range of speech-processing tasks. This paper proposes a method to bias self-supervised learning towards a specific task. The core idea…

Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and difficult to…

Speech foundation models, such as HuBERT and its variants, are pre-trained on large amounts of unlabeled speech data and then used for a range of downstream tasks. These models use a masked prediction objective, where the model learns to…

Self-supervised learning has emerged as a powerful approach for leveraging large-scale unlabeled data to improve model performance in various domains. In this paper, we explore masked self-supervised pre-training for text recognition…

Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been extensively investigated in the supervised setting. This assumes the existence of a parallel corpus of speech and orthographic transcriptions. Recently,…

Learning meaningful and general representations from unannotated speech that are applicable to a wide range of tasks remains challenging. In this paper we propose to use autoregressive predictive coding (APC), a recently proposed…

We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The…

Recently, various neural models for multi-party conversation (MPC) have achieved impressive improvements on a variety of tasks such as addressee recognition, speaker identification and response prediction. However, these existing methods on…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

We present a bidirectional unsupervised model pre-training (UPT) method and apply it to children's automatic speech recognition (ASR). An obstacle to improving child ASR is the scarcity of child speech databases. A common approach to…

Achieving high accuracy with low latency has always been a challenge in streaming end-to-end automatic speech recognition (ASR) systems. By attending to more future contexts, a streaming ASR model achieves higher accuracy but results in…

In recent years, self-supervised pre-training methods have gained significant traction in learning high-level information from raw speech. Among these methods, HuBERT has demonstrated SOTA performance in automatic speech recognition (ASR).…

This study (The work was accomplished during the internship in Tencent AI lab) addresses semi-supervised acoustic modeling, i.e. attaining high-level representations from unsupervised audio data and fine-tuning the parameters of pre-trained…

Transformer-based models attain excellent results and generalize well when trained on sufficient amounts of data. However, constrained by the limited data available in the audio domain, most transformer-based models for audio tasks are…

An increasing number of people in the world today speak a mixed-language as a result of being multilingual. However, building a speech recognition system for code-switching remains difficult due to the availability of limited resources and…

In this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised…

In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert-…

In the development of neural text-to-speech systems, model pre-training with a large amount of non-target speakers' data is a common approach. However, in terms of ultimately achieved system performance for target speaker(s), the actual…