Lombard Speech Model for Automatic Enhancement of Speech Intelligibility over Telephone Channel
This paper aims at evaluating the performance of a “Lombard effect model for improving speech intelli gibility over telephone channel. It is well known that the naturalness and intelligibility of speech degrades rapidly in communication channels, such as phone net works or public address systems. To reduce the degra dation, a Lombard effect mimicking system has been proposed to modify the variations of duration, formant frequencies, formant bandwidth, pitch and energy in each frequency band of normal speech for compensat ing Lombard effect. In order to validate the effective ness of our Lombard effect mimicking system for speech intelligibility improvement, we evaluated synthetic Lom bard speech over telephone channel. From subjective listening test, it is shown that the proposed compensa tion algorithm increases the intelligibility of speech in telephone channel environments at 5 dB Signal-to-Noise ratio (SNR) and 10 dB SNR by nearly 10％ and 13:9％ over the unprocessed signals respectively.
D.-Y. Huang E.P. Ong
Institute for Infocomm Research Agency for Science, Technology and Research (ASTAR) 1 Fusionopolis Way ＃21, Connexis Singapore 119613
国际会议
上海
英文
429-434
2010-10-20（万方平台首次上网日期，不代表论文的发表时间）