DeepAI
Log In Sign Up

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition

11/16/2021
by   Yi-Chang Chen, et al.
0

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 only consider the semantic correction while the phonetic features of words is neglected. The semantic-only post-correction will consequently decrease the performance since homophonic errors are fairly common in Chinese ASR. In this paper, we proposed a novel approach to collectively exploit the contextualized representation and the phonetic information between the error and its replacing candidates to alleviate the error rate of Chinese ASR. Our experiment results on real world speech recognition datasets showed that our proposed method has evidently lower CER than the baseline model, which utilized a pre-trained BERT MLM as the corrector.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/26/2021

BART based semantic correction for Mandarin automatic speech recognition system

Although automatic speech recognition (ASR) systems achieved significant...
11/04/2020

Chinese Grammatical Correction Using BERT-based Pre-trained Model

In recent years, pre-trained models have been extensively studied, and s...
10/13/2022

Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models

Labeled audio data is insufficient to build satisfying speech recognitio...
11/29/2022

Better Transcription of UK Supreme Court Hearings

Transcription of legal proceedings is very important to enable access to...
02/23/2021

Evolutionary optimization of contexts for phonetic correction in speech recognition systems

Automatic Speech Recognition (ASR) is an area of growing academic and co...
01/08/2021

Misspelling Correction with Pre-trained Contextual Language Model

Spelling irregularities, known now as spelling mistakes, have been found...
01/02/2018

A Novel Approach to Skew-Detection and Correction of English Alphabets for OCR

Optical Character Recognition has been a challenging field in the advent...

Code Repositories

phonetic_mlm

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition


view repo