Statistical models for topic identification using phoneme substrings
J. H. Wright, Michael J. Carey, E.S. Parris · IEEE International Conference on Acoustics Speech and Signal Processing · 2002
Phoneme substrings that are recurrent within training data are detected and logged using dynamic programming procedures. The resulting keystrings (cluster centroids) are awarded a usefulness rating based on smoothed occurrence probabilities in wanted and unwanted data. The rankings of the keystrings by usefulness measured on training, development test and final test data for three language-pairs from the OGI multi-language corpus are highly consistent, showing that language-specific features are being found. Statistical measures of local association also suggest that keystring occurrences can be correlated in a manner similar to that of keywords for a particular topic. With improved recognition accuracy it should be possible to exploit this information in order to enhance performance in topic identification.
Cited by 21 works. doi:10.1109/icassp.1996.540419
Authors
References
- Time Warps, String Edits, and Macromolecules: The Theory and Practice of Sequence Comparison
- SWITCHBOARD: telephone speech corpus for research and development
- The Analysis of Contingency Tables
- The OGI multi-language telephone speech corpus
- The Analysis of Contingency Tables
- Application of large vocabulary continuous speech recognition to topic and speaker identification using telephone speech
- Issues in topic identification on the switchboard corpus
- Discriminative phonemes for speaker identification
- Topic discrimination using higher-order statistical models of spotted keywords
- The application of dynamic programming techniques to non-word based topic spotting