发明名称 |
SYSTEM AND METHOD FOR EXTRACTING AND USING PROSODY FEATURES |
摘要 |
A system for carrying out voice pattern recognition and a method for achieving same. The system includes an arrangement for acquiring an input voice, a signal processing library for extracting acoustic and prosodic features of the acquired voice, a database for storing a recognition dictionary, at least one instance of a prosody detector for carrying out a prosody detection process on extracted respective prosodic features, communicating with an end user application for applying control thereto. |
申请公布号 |
US2017103748(A1) |
申请公布日期 |
2017.04.13 |
申请号 |
US201514880363 |
申请日期 |
2015.10.12 |
申请人 |
WEISSBERG Danny Lionel;TIOMKIN Stas |
发明人 |
WEISSBERG Danny Lionel;TIOMKIN Stas |
分类号 |
G10L15/02;G10L15/06;G10L15/22 |
主分类号 |
G10L15/02 |
代理机构 |
|
代理人 |
|
主权项 |
1. A system for voice pattern recognition implementable on input voice, said system comprising:
a voice acquisition means for acquiring said input voice; a signal processing library (208) for extracting acoustic and prosodic features of said input voice; at least one instance of a prosody detector for carrying out a prosody detection process on extracted respective prosodic features; and a database (210) for storing a recognition dictionary based on a predetermined mapping between voice features extracted from voice recording and reference, wherein said system communicates with an end user application (55) for applying control thereto. |
地址 |
Ramat Gan IL |