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 candidate training objectives, we develop a theoretical framework for unsupervised speech recognition grounded in classification error bounds. We introduce two conditions under which unsupervised speech recognition is possible. The necessity of these conditions are also discussed. Under these conditions, we derive a classification error bound for unsupervised speech recognition and validate this bound in simulations. Motivated by this bound, we propose a single-stage sequence-level cross-entropy loss for unsupervised speech recognition.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech RecognitionSimilar Papers 제목 키워드 기반
Progressive Joint Modeling in Unsupervised Single-channel Overlapped Speech Recognition
Unsupervised single-channel overlapped speech recognition is one of the hardest problems in automatic speech recognition (ASR). Permutation invariant training (PIT) is a state of the art model-based approach, which appli…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+2Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only
Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work,…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionAlmost Unsupervised Text to Speech and Automatic Speech Recognition
Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DenoisingLanguage Modeling+5Unsupervised pre-training for sequence to sequence speech recognition
This paper proposes a novel approach to pre-train encoder-decoder sequence-to-sequence (seq2seq) model with unpaired speech and transcripts respectively. Our pre-training method is divided into two stages, named acoustic…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderSequence-To-Sequence Speech Recognition+5Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization
In this paper, we present a novel bilevel optimization-based training approach to training acoustic models for automatic speech recognition (ASR) tasks that we term {bi-level joint unsupervised and supervised training (B…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Bilevel Optimizationspeech-recognition+1