Invention Grant
US09280968B2 System and method of using neural transforms of robust audio features for speech processing
有权
用于语音处理的鲁棒音频特征的神经变换的系统和方法
- Patent Title: System and method of using neural transforms of robust audio features for speech processing
- Patent Title (中): 用于语音处理的鲁棒音频特征的神经变换的系统和方法
-
Application No.: US14046393Application Date: 2013-10-04
-
Publication No.: US09280968B2Publication Date: 2016-03-08
- Inventor: Enrico Luigi Bocchieri , Dimitrios Dimitriadis
- Applicant: AT&T Intellectual Property I, L.P.
- Applicant Address: US GA Atlanta
- Assignee: AT&T Intellectual Property I, L.P.
- Current Assignee: AT&T Intellectual Property I, L.P.
- Current Assignee Address: US GA Atlanta
- Main IPC: G10L15/16
- IPC: G10L15/16 ; G10L21/02 ; G10L19/00 ; G10L15/02 ; G10L21/0208 ; G10L15/14
Abstract:
A system and method for processing speech includes receiving a first information stream associated with speech, the first information stream comprising micro-modulation features and receiving a second information stream associated with the speech, the second information stream comprising features. The method includes combining, via a non-linear multilayer perceptron, the first information stream and the second information stream to yield a third information stream. The system performs automatic speech recognition on the third information stream. The third information stream can also be used for training HMMs.
Public/Granted literature
- US20150100312A1 SYSTEM AND METHOD OF USING NEURAL TRANSFORMS OF ROBUST AUDIO FEATURES FOR SPEECH PROCESSING Public/Granted day:2015-04-09
Information query
