Loading...
Please wait, while we are loading the content...
Similar Documents
An evaluation of target speech for nonaudible murmur enhancement focusing on its intelligibility under noisy environments
Content Provider | Semantic Scholar |
---|---|
Author | Sakura, Tsuruta Kou, Tanaka Tomoki, Toda Neubig, Graham Sakriani, Sakti Satoshi, Nakamura |
Copyright Year | 2014 |
Abstract | Nonaudible murmur (NAM) is a soft whispered voice recorded with a NAM microphone through body conduction. NAM is effective for silent speech communication as it allows a speaker to speak without making an audible sound. However, its intelligibility and naturalness are significantly degraded compared to natural speech owing to acoustic changes caused by body conduction. To address this issue, statistical voice conversion methods from NAM to normal speech (NAM-to-Speech) and to a whispered voice (NAM-to-Whisper) have been proposed. It has been reported that these NAM enhancement methods significantly improve speech quality and intelligibility of NAM, and that NAM-to-Whisper is more effective than NAM-to-Speech. However, it is still not obvious which method is more effective if a listener listens to the enhanced speech in noisy environments, a situation that often happens in silent speech communication. In this report, we assume a situation where NAM is uttered by a speaker in a quiet environment and conveyed to a listener in a noisy environment, and investigate what kinds of target speech is more effective for NAM enhancement. We also propose NAM enhancement methods for converting NAM to other types of target voiced speech. Experimental results show that the conversion process into voiced speech is more effective than that into unvoiced speech for generating more intelligible speech in noisy environments. |
Starting Page | 71 |
Ending Page | 76 |
Page Count | 6 |
File Format | PDF HTM / HTML |
Volume Number | 114 |
Alternate Webpage(s) | https://ahcweb01.naist.jp/papers/conference/2014/201411_SIGSP_Tsuruta_1/201411_SIGSP_Tsuruta_1.paper.pdf |
Language | English |
Access Restriction | Open |
Content Type | Text |
Resource Type | Article |