发明名称 |
SPEECH SEGMENT DETECTION DEVICE, VOICE PROCESSING SYSTEM, SPEECH SEGMENT DETECTION METHOD, AND PROGRAM |
摘要 |
A server device (20) according to an embodiment is provided with a communications unit (21) and a second detection unit (22). The communications unit (21) receives a first voice signal, which is a signal with a likelihood representing a speech-like nature having a first threshold value or greater, from a client device (10). The second detection unit (22) detects a second voice signal, which is a signal for a segment with a likelihood representing a speech-like nature having a second threshold value, which is greater than the first threshold value, or greater, from the first voice signal received from the client device (10). |
申请公布号 |
WO2016017229(A1) |
申请公布日期 |
2016.02.04 |
申请号 |
WO2015JP63533 |
申请日期 |
2015.05.11 |
申请人 |
KABUSHIKI KAISHA TOSHIBA;TOSHIBA SOLUTIONS CORPORATION |
发明人 |
CHIYO, KENTA;KANO, TOSHIYUKI |
分类号 |
G10L15/30;G10L15/04;G10L25/78 |
主分类号 |
G10L15/30 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|