Abstract | ||
---|---|---|
A hierarchical approach to phonemic segmentation of continuous, speaker-independent speech is presented. Each sentence is divided into distinct obstruent and sonorant regions using a Bayesian decision surface. Rules are then used to make context specific corrections with these regions. Finally, finer segmentation is performed using a number of rules specific to obstruent and sonorant boundaries. Around 80% of the boundaries are located with an insertion rate of 12%. The developed system is suitable for use in phoneme recognition and automatic labelling of speech |
Year | DOI | Venue |
---|---|---|
1994 | 10.1109/ICASSP.1994.389352 | Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference |
Keywords | Field | DocType |
Bayes methods,acoustic signal processing,speech processing,speech recognition,Bayesian decision surface,automatic speech labelling,continuous speaker-independent speech,continuous speech recognition,fluent speech,insertion rate,obstruent boundaries,obstruent regions,phoneme recognition,phonemic segmentation,sentence,sonorant boundaries,sonorant regions | Speech processing,Pattern recognition,Audio mining,Computer science,Segmentation,Speech recognition,Obstruent,Speaker recognition,Artificial intelligence,Sonorant,Sentence,Acoustic model | Conference |
Volume | ISSN | ISBN |
i | 1520-6149 | 0-7803-1775-0 |
Citations | PageRank | References |
22 | 1.90 | 7 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
David B. Grayden | 1 | 32 | 6.82 |
Michael S. Scordilis | 2 | 155 | 15.56 |