Speech Recognition by Simply Fine-tuning BERT
We propose a simple method for automatic speech recognition (ASR) by fine-tuning BERT, which is a language model (LM) trained on large-scale unlabeled text data and can generate rich contextual representations. Our assumption is that given a history context sequence, a powerful LM can narrow the range of possible choices and the speech signal can be used as a simple clue. Hence, comparing to conventional ASR systems that train a powerful acoustic model (AM) from scratch, we believe that speech recognition is possible by simply fine-tuning a BERT model. As an initial study, we demonstrate the effectiveness of the proposed idea on the AISHELL dataset and show that stacking a very simple AM on top of BERT can yield reasonable performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modellingspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding
Speech self-supervised models such as wav2vec 2.0 and HuBERT are making revolutionary progress in Automatic Speech Recognition (ASR). However, they have not been totally proven to produce better performance on tasks othe…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Emotion Recognitionintent-classification+8Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition
Multimodal emotion recognition from speech is an important area in affective computing. Fusing multiple data modalities and learning representations with limited amounts of labeled data is a challenging task. In this pap…
Jointly Fine-Tuning “BERT-like” Self Supervised Models to Improve Multimodal Speech Emotion Recognition
Multimodal emotion recognition from speech is an important area in affective computing. Fusing multiple data modalities and learning representations with limited amounts of labeled data is a challenging task. In this pap…
Emotion RecognitionMultimodal Deep LearningMultimodal Emotion RecognitionMultimodal Sentiment Analysis+4SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations
There is a growing interest in cost-effective self-supervised fine-tuning (SSFT) of self-supervised learning (SSL)-based speech models to obtain task-specific representations. These task-specific representations are used…
Automatic Speech RecognitionData AugmentationGPUPhoneme Recognition+3Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition
Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing app…
Language ModelingLanguage ModellingRepresentation Learningspeech-recognition+2