Conference paper
Pi-sigma and hidden control based self-structuring models for text-independent speaker recognition
Two text-independent speaker recognition methods based on self-structuring hidden control (SHC) neural models and self-structuring pi-sigma (SPS) neural models are proposed. The authors have designed the self-structuring models to achieve better model structures, i.e., data determined architectures instead of a priori determined architectures.
PS and HC neural models for speaker recognition are also proposed. Each of the four methods requires typically 75% fewer neural models compared with the predictive neural network based text-independent speaker recognition method, i.e., the latter contains an ergodic M-state model using M neural models (M=4) for each speaker; here, each of the speaker recognition systems uses only one neural model to realize an ergodic M-state model.
The pi-sigma models have been modified to obtain self-structuring PS models and the speech recognition SHC models have been changed to fit into speaker recognition systems.<>
Language: | English |
---|---|
Year: | 1993 |
Pages: | 537,538,539,540 |
Proceedings: | Proceedings of ICASSP '93 |
ISBN: | 0780309464 , 0780374029 , 9780780309463 and 9780780374027 |
ISSN: | 2379190x and 15206149 |
Types: | Conference paper |
DOI: | 10.1109/ICASSP.1993.319174 |
Binary codes Hidden Markov models Laboratories Microphones Neural networks Predictive models Security Speaker recognition Speech recognition Vector quantization data determined architectures ergodic M-state model hidden control based self-structuring models model structures neural models neural nets pi-sigma models speech recognition text-independent speaker recognition