Computational auditory scene analysis and its application to robot audition

被引：0

作者：

Okuno, Hiroshi G. ^{[1
]}

Nakadai, Kazuhiro ^{[2
]}

机构：

[1] Kyoto Univ, Grad Sch Informat, Sakyo Ku, Kyoto 6068501, Japan

[2] Honda Res Inst Japan Co Ltd, Saitama 3510188, Japan

来源：

2008 HANDS-FREE SPEECH COMMUNICATION AND MICROPHONE ARRAYS | 2008年

关键词：

robot audition; computational auditory scene analysis; Missing feature theory; simultaneous speakers;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Robot capability of hearing sounds, in particular, a mixture of sounds, by its own microphones, that is, robot audition, is important in improving human robot interaction. This paper presents the robot audition open-source software, called "HARK" (HRI-JP Audition for Robots with Kyoto University), which consists of primitive functions in computational auditory scene analysis; sound source localization, separation, and recognition of separated sounds. Since separated sounds suffer from spectral distortion due to separation, the HARK generates a time-spectral map of reliability, called "missing feature mask", for features of separated sounds. Then separated sounds are recognized by the Missing-Feature Theory (MFT) based ASR with missing feature masks. The HARK is implemented on the middle-ware called "FlowDesigner" to share intermediate audio data, which enables near real-time processing.

引用

页码：125 / +

页数：2