Automatic speech segmentation for Chinese speech database based on HMM
Research output: Contribution to book/Conference proceedings/Anthology/Report › Conference contribution › Contributed › peer-review
Contributors
Abstract
The paper offers an optimized method in speech segmentation of Mandarin speech database by using Hidden Markov Model (HMM). The method takes the syllable boundaries into account. Testing shows that the accuracy of results is improved to 95% from 88% compared to the normal method. Especially, most of the boundaries between two vowels can also be well detected with the new method. The paper also analyzes the influence of the amount of HMM states and the amount of the training corpus.
Details
| Original language | English |
|---|---|
| Title of host publication | 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering. TENCOM '02. Proceedings |
| Editors | BZ Yuan, XF Tang |
| Publisher | Wiley-IEEE Press |
| Pages | 481-484 |
| Number of pages | 4 |
| Volume | 1 |
| ISBN (print) | 0-7803-7490-8 |
| Publication status | Published - 2002 |
| Peer-reviewed | Yes |
| Externally published | Yes |
Conference
| Title | IEEE Region 10 Technical Conference on Computers, Communications, Control and Power Engineering |
|---|---|
| Abbreviated title | TENCOM 2002 |
| Duration | 28 - 31 October 2002 |
| City | Beijing |
| Country | China |
External IDs
| Scopus | 0038337070 |
|---|---|
| ORCID | /0000-0001-5973-5026/work/142253745 |
Keywords
Keywords
- speech segmentation, hidden Markov model