Chinese-English bilingual speech recognition method based on phoneme confusion

Abstract

The invention relates to a Chinese-English bilingual speech recognition method based on phoneme confusion. The method comprises the following steps: unifying a Chinese-English phoneme set by adopting a twice phoneme clustering method, obtaining a Chinese-English mixed acoustic model by retraining, correcting corresponding bilingual pronunciation dictionaries, and realizing Chinese-English bilingual recognition by a decoder based on the preceding steps. The Chinese recognition rate of a Chinese-English bilingual speech recognition system based on TCM phoneme confusion can be comparable to that of an independent Chinese speech recognition system; on the premise that English data with Chinese accent is unavailable and standard Chinese-English training data are used only, compared with the relatively independent English speech recognition system, recognition of English fragments with the Chinese accent is obviously improved; meanwhile, the Chinese-English bilingual speech recognition system based on the TCM phoneme confusion also has a better recognition performance than the existing common bilingual recognition system which performs phoneme clustering by virtue of a logarithm likelihood criterion, and has very high practicability.

Description

technical field [0001] The present invention relates to a bilingual speech recognition method, more specifically, the present invention relates to a Chinese-English bilingual recognition method based on a two-pass phone clustering method based on Confusion Matrix (TCM: Two-pass phone clustering method based on Confusion Matrix). Background technique [0002] With the globalization of information in modern society, bilingual and multilingual communication has become more and more common, which brings new challenges to speech recognition technology. In bilingual recognition, the main problem is that the speaker will intersperse the second language in the process of speaking the mother tongue, and the inserted second language has the pronunciation characteristics of the speaker's mother tongue (nonnative). How to achieve and improve the recognition of the second language with the pronunciation characteristics of the mother tongue under the premise of ensuring the speech recogni...

AI Technical Summary

Problems solved by technology

In bilingual recognition, the main problem is that the speaker will intersperse the second language in the process of speaking the mother tongue, and the inserted second language has the pronunciation characteristics of the speaker's mother tongue (nonnative)

The main problem here is that the log-likelihood criterion is a clustering criterion based on the observation probability of the same speech feature vector sequence under different phoneme Gaussian models, but in fact only the observation probability under the Gaussian model determines whether the similarity between two phonemes is correct. reliable

Images