Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM
Connectionist temporal classification (CTC) -based models are attractive in automatic speech recognition (ASR) because of their non-autoregressive nature. To take advantage of text-only data, language model (LM) integration approaches such as rescoring and shallow fusion have been widely used for CTC. However, they lose CTC's non-autoregressive nature because of the need for beam search, which slows down the inference speed. In this study, we propose an error correction method with phone-conditioned masked LM (PC-MLM). In the proposed method, less confident word tokens in a greedy decoded output from CTC are masked. PC-MLM then predicts these masked word tokens given unmasked words and phones supplementally predicted from CTC. We further extend it to Deletable PC-MLM in order to address insertion errors. Since both CTC and PC-MLM are non-autoregressive models, the method enables fast LM integration. Experimental evaluations on the Corpus of Spontaneous Japanese (CSJ) and TED-LIUM2 in domain adaptation setting shows that our proposed method outperformed rescoring and shallow fusion in terms of inference speed, and also in terms of recognition accuracy on CSJ.
Code (1)
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Domain AdaptationLanguage ModelingLanguage Modellingspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Graph-Based Phonetic Error Correction of Noisy ASR
Automatic speech recognition (ASR) systems, despite low overall word error rates, produce residual lexical errors that disproportionately affect semantically critical tokens such as named entities, negations, and sentime…
Graph Neural NetworkSpeech RecognitionNon-Autoregressive Chinese ASR Error Correction with Phonological Training
Automatic Speech Recognition (ASR) is an efficient and widely used input method that transcribes speech signals into text. As the errors introduced by ASR systems will impair the performance of downstream tasks, we intro…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Sentencespeech-recognition+1Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition
Due to the recent advances of natural language processing, several works have applied the pre-trained masked language model (MLM) of BERT to the post-correction of speech recognition. However, existing pre-trained models…
Language ModelingLanguage Modellingspeech-recognitionSpeech RecognitionMaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer
The recent large-scale text-to-speech (TTS) systems are usually grouped as autoregressive and non-autoregressive systems. The autoregressive systems implicitly model duration but exhibit certain deficiencies in robustnes…
Self-Supervised Learningtext-to-speechText to SpeechDCGC: Draft-Conditioned Global Correction for Complex Reasoning with Masked Diffusion Models
Correcting flawed reasoning traces remains a significant challenge for Large Language Models (LLMs), whose autoregressive generation can propagate early mistakes into subsequent reasoning. We introduce DCGC, a Masked Dif…