Invention Grant
US07930178B2 Speech modeling and enhancement based on magnitude-normalized spectra
有权
基于幅度归一化光谱的语音建模和增强
- Patent Title: Speech modeling and enhancement based on magnitude-normalized spectra
- Patent Title (中): 基于幅度归一化光谱的语音建模和增强
-
Application No.: US11317269Application Date: 2005-12-23
-
Publication No.: US07930178B2Publication Date: 2011-04-19
- Inventor: Zhengyou Zhang , Alejandro Acero , Amarnag Subramanya , Zicheng Liu
- Applicant: Zhengyou Zhang , Alejandro Acero , Amarnag Subramanya , Zicheng Liu
- Applicant Address: US WA Redmond
- Assignee: Microsoft Corporation
- Current Assignee: Microsoft Corporation
- Current Assignee Address: US WA Redmond
- Agency: Westman, Champlin & Kelly, P.A.
- Agent Theodore M. Magee
- Main IPC: G10L19/14
- IPC: G10L19/14 ; G10L15/20 ; G10L21/02
Abstract:
A frame of a speech signal is converted into the spectral domain to identify a plurality of frequency components and an energy value for the frame is determined. The plurality of frequency components is divided by the energy value for the frame to form energy-normalized frequency components. A model is then constructed from the energy-normalized frequency components and can be used for speech recognition and speech enhancement.
Public/Granted literature
- US20070150263A1 Speech modeling and enhancement based on magnitude-normalized spectra Public/Granted day:2007-06-28
Information query
