Invention Grant
- Patent Title: Data augmentation method based on stochastic feature mapping for automatic speech recognition
-
Application No.: US14977674Application Date: 2015-12-22
-
Publication No.: US09824683B2Publication Date: 2017-11-21
- Inventor: Xiaodong Cui , Vaibhava Goel , Brian E. D. Kingsbury
- Applicant: International Business Machines Corporation
- Applicant Address: US NY Armonk
- Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Current Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Current Assignee Address: US NY Armonk
- Agency: Otterstedt, Ellenbogen & Kammer, LLP
- Agent David M. Quinn
- Main IPC: G10L15/00
- IPC: G10L15/00 ; G10L15/06 ; G10L21/0272 ; G10L15/16 ; G10L15/02

Abstract:
A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.
Public/Granted literature
- US20170200446A1 DATA AUGMENTATION METHOD BASED ON STOCHASTIC FEATURE MAPPING FOR AUTOMATIC SPEECH RECOGNITION Public/Granted day:2017-07-13
Information query