Bandwidth mismatch compensation for robust speech recognition

Yuan Fu Liao, Jeng Shien Lin, Wei Ho Tsai

研究成果同行評審

3 引文 斯高帕斯(Scopus)

摘要

In this paper, an iterative bandwidth mismatch compensation (BMC) algorithm is proposed to alleviate the need of multiple pre-trained models for recognizing different bandwidth speech. The BMC uses the concept of the bandwidth extension as similar as in the speech enhancement approaches. However, it aims at directly improving the recognition accuracy instead of speech intelligence or quality and utilizes only recognizer?s hidden Markov models (HMMs) for both bandwidth mismatch compensation and recognition. The BMC first detects the bandwidth of the input speech signal based on a divergence measurement. The HMM/Gaussian mixture model (GMM)- based method is then used to iteratively segment the input speech utterance and compensates the speech features. Experiments on serious bandwidth mismatched conditions, i.e., training on 8 kHz and testing on 4 kHz or 5.5 kHz bandwidth database have verified the effectiveness of the proposed approach.

原文English
頁面3093-3096
頁數4
出版狀態Published - 2003
事件8th European Conference on Speech Communication and Technology, EUROSPEECH 2003 - Geneva, 瑞士
持續時間: 1 9月 20034 9月 2003

Conference

Conference8th European Conference on Speech Communication and Technology, EUROSPEECH 2003
國家/地區瑞士
城市Geneva
期間1/09/034/09/03

指紋

深入研究「Bandwidth mismatch compensation for robust speech recognition」主題。共同形成了獨特的指紋。

引用此