The improvements on automatic mandarin pronunciation evaluation
Computer Science and Network Technology(2012)
Abstract
Automatic pronunciation evaluation (APE) often works in noise environment. With MFCC based automatic speech recognizer (ASR) embedded, APE's noise robustness is not usually satisfied. Since it improves anti-noise performances of ASR, power normalized cepstrum coefficient (PNCC) [1] is introduced i n t o APE in this paper. Experiment of noise environment shows improvement in both APE and recognition performances. In order to discriminate mispronunciation APE needs standard “golden” acoustic models. The speaker adaptation models of APE need to be trained by standard pronounced utterances of target speaker. But standard pronunciation is not usually expected in APE. In this paper a new speaker adaptation strategy is suggested. A recognizer of speaker independent (SI) is used to selected correct pronounced utterances for adaptation training. The adapted system achieved better score correlation with subjective scores.
MoreTranslated text
Key words
cepstral analysis,correlation methods,natural language processing,performance evaluation,speaker recognition,ape,asr,mfcc,pncc,si recognizer,adaptation training,antinoise performance improvement,automatic mandarin pronunciation evaluation,automatic speech recognizer,mispronunciation,noise robustness,power normalized cepstrum coefficient,recognition performances,score correlation,speaker adaptation models,speaker independent recognizer,standard golden acoustic models,standard pronounced utterances,subjective scores,pronunciation evaluation,anti-noise,speaker adaptation,speech recognition
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined