发明名称 |
Noise adaptation system of speech model, noise adaptation method, and noise adaptation program for speech recognition |
摘要 |
An object of the present invention is to facilitate dealing with noisy speech with varying SNR and save calculation costs by generating a speech model with a single-tree-structure and using the model for speech recognition. Every piece of noise data stored in a noise database is used under every SNR condition to calculate the distance between all noise models with the SNR conditions and the noise-added speech is clustered. Based on the result of the clustering, a single-tree-structure model space into which the noise and SNR are integrated is generated (steps S 1 to S 5 ). At a noise extraction step (step S 6 ), inputted noisy speech to be recognized is analyzed to extract a feature parameter string and the likelihoods of HMMs are compared one another to select an optimum model from the tree-structure noisy speech model space (step S 7 ). Linear transformation is applied to the selected noisy speech model space so that the likelihood is maximized (step S 8 ).
|
申请公布号 |
US7424426(B2) |
申请公布日期 |
2008.09.09 |
申请号 |
US20040920461 |
申请日期 |
2004.08.18 |
申请人 |
SADAOKI FURUI AND NTT DOCOMO, INC. |
发明人 |
FURUI SADAOKI;ZHANG ZHIPENG;HORIKOSHI TSUTOMU;SUGIMURA TOSHIAKI |
分类号 |
G10L15/00;G10L15/02;G10L15/06;G10L15/14;G10L15/20 |
主分类号 |
G10L15/00 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|