Automatic phonetic segmentation of malay speech database
This paper deals with automatic phonetic segmentation for Malay continuous speech. This study investigates fast and automatic phone segmentation in preparing database for Malay concatenative Text-to-Speech (TTS) systems. A 35 Malay phone set has been chosen, which is suitable for building Malay TTS....
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
2007
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/7635/1/Sheikh_Hussain_Shaikh_2007_Automatic_Phonetic_Segmentation_of_Malay_Speech.pdf http://eprints.utm.my/7635/ http://dx.doi.org/10.1109/ICICS.2007.4449574 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1845471847936688128 |
|---|---|
| author | Ting, Chee Ming Shaikh Salleh, Sheikh Hussain Tan, Tian Swee Ariff, Ahmad Kamarul |
| author_facet | Ting, Chee Ming Shaikh Salleh, Sheikh Hussain Tan, Tian Swee Ariff, Ahmad Kamarul |
| author_sort | Ting, Chee Ming |
| building | UTM Library |
| collection | Institutional Repository |
| content_provider | Universiti Teknologi Malaysia |
| content_source | UTM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | This paper deals with automatic phonetic segmentation for Malay continuous speech. This study investigates fast and automatic phone segmentation in preparing database for Malay concatenative Text-to-Speech (TTS) systems. A 35 Malay phone set has been chosen, which is suitable for building Malay TTS. The segmentation experiment is based on this phone set. HMM based segmentation approach which uses Viterbi force alignment technique is adapted. We use continuous density HMM (CDHMM) with Gaussian mixture which is performs well in speech recognition to prevent large segmentation errors. Besides, this paper presents an implicit boundary refinement method that is incorporated in the Viterbi phonetic alignment. In this approach, the HMM model is trained with phone tokens with their boundaries extended to the be-side phones. This increases the ability of the HMM in modeling phone boundaries and provides effect of implicit boundary refinement when used in phonetic alignment thus reduce segmentation errors. This approach improves increase the performance of baseline HMM segmentation from 42.39%, 74.83%, 84.34% of automatic boundary marks within error smaller than 5, 15, and 25ms to 47.75%, 76.38%, 85.55%. |
| format | Conference or Workshop Item |
| id | my.utm.eprints-7635 |
| institution | Universiti Teknologi Malaysia |
| language | en |
| publishDate | 2007 |
| record_format | eprints |
| spelling | my.utm.eprints-76352010-06-01T15:54:10Z http://eprints.utm.my/7635/ Automatic phonetic segmentation of malay speech database Ting, Chee Ming Shaikh Salleh, Sheikh Hussain Tan, Tian Swee Ariff, Ahmad Kamarul TK Electrical engineering. Electronics Nuclear engineering This paper deals with automatic phonetic segmentation for Malay continuous speech. This study investigates fast and automatic phone segmentation in preparing database for Malay concatenative Text-to-Speech (TTS) systems. A 35 Malay phone set has been chosen, which is suitable for building Malay TTS. The segmentation experiment is based on this phone set. HMM based segmentation approach which uses Viterbi force alignment technique is adapted. We use continuous density HMM (CDHMM) with Gaussian mixture which is performs well in speech recognition to prevent large segmentation errors. Besides, this paper presents an implicit boundary refinement method that is incorporated in the Viterbi phonetic alignment. In this approach, the HMM model is trained with phone tokens with their boundaries extended to the be-side phones. This increases the ability of the HMM in modeling phone boundaries and provides effect of implicit boundary refinement when used in phonetic alignment thus reduce segmentation errors. This approach improves increase the performance of baseline HMM segmentation from 42.39%, 74.83%, 84.34% of automatic boundary marks within error smaller than 5, 15, and 25ms to 47.75%, 76.38%, 85.55%. 2007-12 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.utm.my/7635/1/Sheikh_Hussain_Shaikh_2007_Automatic_Phonetic_Segmentation_of_Malay_Speech.pdf Ting, Chee Ming and Shaikh Salleh, Sheikh Hussain and Tan, Tian Swee and Ariff, Ahmad Kamarul (2007) Automatic phonetic segmentation of malay speech database. In: Information, Communications & Signal Processing, 2007 6th International Conference, 10-13 Dec 2007, Singapore. http://dx.doi.org/10.1109/ICICS.2007.4449574 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Ting, Chee Ming Shaikh Salleh, Sheikh Hussain Tan, Tian Swee Ariff, Ahmad Kamarul Automatic phonetic segmentation of malay speech database |
| title | Automatic phonetic segmentation of malay speech database |
| title_full | Automatic phonetic segmentation of malay speech database |
| title_fullStr | Automatic phonetic segmentation of malay speech database |
| title_full_unstemmed | Automatic phonetic segmentation of malay speech database |
| title_short | Automatic phonetic segmentation of malay speech database |
| title_sort | automatic phonetic segmentation of malay speech database |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://eprints.utm.my/7635/1/Sheikh_Hussain_Shaikh_2007_Automatic_Phonetic_Segmentation_of_Malay_Speech.pdf http://eprints.utm.my/7635/ http://dx.doi.org/10.1109/ICICS.2007.4449574 |
| url_provider | http://eprints.utm.my/ |