Speaker normalization for speech recognition
- 1 January 1992
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
A codeword-dependent neural network (CDNN) is presented for the study of speaker adaptation. The CDNN is used as a nonlinear mapping function to transform speech data between two speakers. The mapping function is characterized by a number of important properties. First, the assembly of mapping functions enhances overall mapping quality. Second, multiple input vectors are used simultaneously in the transformation. This not only makes full use of dynamic information but also alleviates possible errors in the supervision data. Finally, the mapping function is derived from training data, with the quality dependent on the available amount of training data. Based on speaker-dependent models, performance evaluation showed that speaker normalization significantly reduced the error rate from 41.9% to 5.0%.Keywords
This publication has 17 references indexed in Scilit:
- Rapid speaker adaptation using a probabilistic spectral mappingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Spectral transformations through canonical correlation analysis for speaker adptation in ASRPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Consonant recognition by modular construction of large phonemic time-delay neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Speech recognition using temporal decomposition and multi-layer feed-forward automataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Environmental robustness in automatic speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Speaker-independent word recognition using a neural prediction modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A comparative study of spectral mapping for speaker adaptationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Fast speaker adaptation for speech recognition systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- DARPA resource management benchmark test results June 1990Published by Association for Computational Linguistics (ACL) ,1990
- An Algorithm for Vector Quantizer DesignIEEE Transactions on Communications, 1980