相关论文: wav2vec 2.0: A Framework for Self-Supervised Learn…

Spoken language understanding (SLU) tasks are usually solved by first transcribing an utterance with automatic speech recognition (ASR) and then feeding the output to a text-based model. Recent advances in self-supervised representation…

The current lyrics transcription approaches heavily rely on supervised learning with labeled data, but such data are scarce and manual labeling of singing is expensive. How to benefit from unlabeled data and alleviate limited data problem…

Wav2vec 2.0 is an end-to-end framework of self-supervised learning for speech representation that is successful in automatic speech recognition (ASR), but most of the work on the topic has been developed with a single language: English.…

Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the…

Explaining the decisions made by audio spoofing detection models is crucial for fostering trust in detection outcomes. However, current research on the interpretability of detection models is limited to applying XAI tools to post-trained…

Pre-trained acoustic representations such as wav2vec and DeCoAR have attained impressive word error rates (WER) for speech recognition benchmarks, particularly when labeled data is limited. But little is known about what phonetic properties…

Recent research in speech processing exhibits a growing interest in unsupervised and self-supervised representation learning from unlabelled data to alleviate the need for large amounts of annotated data. We investigate several popular…

We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functions. We perform experiments on the standard LibriSpeech…

Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of…

Self-training (ST) and self-supervised learning (SSL) methods have demonstrated strong improvements in automatic speech recognition (ASR). In spite of these advances, to the best of our knowledge, there is no analysis of how the composition…

Visual Speech Recognition (VSR) differs from the common perception tasks as it requires deeper reasoning over the video sequence, even by human experts. Despite the recent advances in VSR, current approaches rely on labeled data to fully…

Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR). However, the robustness impact of combining the two…

State-of-the-art automatic speech recognition (ASR) systems are trained with tens of thousands of hours of labeled speech data. Human transcription is expensive and time consuming. Factors such as the quality and consistency of the…

This paper proposes a powerful Visual Speech Recognition (VSR) method for multiple languages, especially for low-resource languages that have a limited number of labeled data. Different from previous methods that tried to improve the VSR…

In self-supervised learning for speaker recognition, pseudo labels are useful as the supervision signals. It is a known fact that a speaker recognition model doesn't always benefit from pseudo labels due to their unreliability. In this…

Video recordings of speech contain correlated audio and visual information, providing a strong signal for speech representation learning from the speaker's lip movements and the produced sound. We introduce Audio-Visual Hidden Unit BERT…

With the rise of bidirectional encoder representations from Transformer models in natural language processing, the speech community has adopted some of their development methodologies. Therefore, the Wav2Vec models were introduced to reduce…

Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…

The goal of self-supervised learning (SSL) for automatic speech recognition (ASR) is to learn good speech representations from a large amount of unlabeled speech for the downstream ASR task. However, most SSL frameworks do not consider…

We present a novel approach to any-to-one (A2O) voice conversion (VC) in a sequence-to-sequence (seq2seq) framework. A2O VC aims to convert any speaker, including those unseen during training, to a fixed target speaker. We utilize…