Multiple description quantization for recognizing voice over packet networks

I. Te Lin*, Chun Feng Wu, Sin Horng Chen, Wen Whei Chang

*Corresponding author for this work

研究成果: Conference contribution同行評審

摘要

The practical design of multiple description vector quantizers for robust distributed speech recognition over packet networks is investigated. In the proposed system, speech parameters are quantized and mapped to multiple descriptions for transmission over independent channels. A new approach to the index assignment optimization is presented on the basis of a linear programming framework. Also, a fast local search algorithm is proposed to find the optimal index assignment without compromising the speech recognition accuracy. Experiments with random packet loss in a range of loss conditions are conducted on the Mandarin digit string recognition task. Simulation results indicate that the proposed multiple description scheme provides more robust performance than the ETSI standardized split vector quantization scheme with a single description.

原文English
主出版物標題First International Conference on Communications and Networking in China, ChinaCom '06
發行者IEEE Computer Society
ISBN(列印)1424404630, 9781424404636
DOIs
出版狀態Published - 1 一月 2006
事件1st International Conference on Communications and Networking in China, ChinaCom '06 - Beijing, China
持續時間: 25 十月 200627 十月 2006

出版系列

名字First International Conference on Communications and Networking in China, ChinaCom '06

Conference

Conference1st International Conference on Communications and Networking in China, ChinaCom '06
國家China
城市Beijing
期間25/10/0627/10/06

指紋 深入研究「Multiple description quantization for recognizing voice over packet networks」主題。共同形成了獨特的指紋。

引用此