Towards End-to-end Unsupervised Speech Recognition
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 making supervised speech recognition end-to-end, we introduce wav2vec-U 2.0 which does away with all audio-side pre-processing and improves accuracy through better architecture. In addition, we introduce an auxiliary self-supervised objective that ties model predictions back to the input. Experiments show that wav2vec-U 2.0 improves unsupervised recognition results across different languages while being conceptually simpler.
Code (1)
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionUnsupervised Speech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Study
Unsupervised speech recognition is a task of training a speech recognition model with unpaired data. To determine when and how unsupervised speech recognition can succeed, and how classification error relates to candidat…
Speech RecognitionImproving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis
This paper investigates the use of unsupervised text-to-speech synthesis (TTS) as a data augmentation method to improve accented speech recognition. TTS systems are trained with a small amount of accented speech training…
Accented Speech RecognitionAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentation+7Unsupervised Automatic Speech Recognition: A Review
Automatic Speech Recognition (ASR) systems can be trained to achieve remarkable performance given large amounts of manually transcribed speech, but large labeled data sets can be difficult or expensive to acquire for all…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionClustering and Mining Accented Speech for Inclusive and Fair Speech Recognition
Modern automatic speech recognition (ASR) systems are typically trained on more than tens of thousands hours of speech data, which is one of the main factors for their great success. However, the distribution of such dat…
Analyzing the Robustness of Unsupervised Speech Recognition
Unsupervised speech recognition (unsupervised ASR) aims to learn the ASR system with non-parallel speech and text corpus only. Wav2vec-U has shown promising results in unsupervised ASR by self-supervised speech represent…
Generative Adversarial Networkspeech-recognitionSpeech RecognitionUnsupervised Speech Recognition