Tài liệu tham khảo |
Loại |
Chi tiết |
1. Đặng Ngọc Đức, Lương Chi Mai “Tăng cường độ chính xác của hệ thống mạng nơ ron nhận dạng tiếng Việt”, Tạp chí Bưu chính Viễn thông - Chuyên san các công trình nghiên cứu và triển khai Công nghệ thông tin và Viễn thông, 11, 75-81 |
Sách, tạp chí |
Tiêu đề: |
Tăng cường độ chính xác của hệ thống mạng nơ ron nhận dạng tiếng Việt |
|
18. Chistikov, P. G.; Korolkov, E. A. và Talanov “Combining HMM and unit selection technologies to increase naturalness of synthesized speech,” Proc. in 19th International Computational Linguistics Conference, Naro-Fominsk, Russia |
Sách, tạp chí |
Tiêu đề: |
Combining HMM and unit selection technologies to increase naturalness of synthesized speech |
|
22. Dung, T.N., Mixdorff, H. et al, “Fujisaki Model based F0 contours in Vietnamese TTS”, In Proceedings of ICSLP2004, Jeju, South Korea |
Sách, tạp chí |
Tiêu đề: |
Fujisaki Model based F0 contours in Vietnamese TTS |
|
23. Demiroglu, “A Small Footprint Hybrid Statistical and Unit Selection Text-to-Speech Synthesis System for Turkish,” Proc. in ICASSP,Kyoto, Japan, tr. 4537-4540 |
Sách, tạp chí |
Tiêu đề: |
A Small Footprint Hybrid Statistical and Unit Selection Text-to-Speech Synthesis System for Turkish |
|
24. Dusterhoff, K. and Black, “Generating F0 contours for speech synthesis using the Tilt intonation theory”, Proceedings of ESCA Workshop of Intonation, pp 107-110, September, Athens, Greece |
Sách, tạp chí |
Tiêu đề: |
Generating F0 contours for speech synthesis using the Tilt intonation theory |
|
27. Guner, E. và Demiroglu, C. (2012), “A Small Footprint Hybrid Statistical and Unit Selection Text-to-Speech Synthesis System for Turkish,” Proc. in ICASSP, Kyoto, Japan, tr. 4537-4540 |
Sách, tạp chí |
Tiêu đề: |
A Small Footprint Hybrid Statistical and Unit Selection Text-to-Speech Synthesis System for Turkish |
Tác giả: |
Guner, E. và Demiroglu, C |
Năm: |
2012 |
|
28. C. Hanilỗi and T. Kinnunen, “Source Cell-Phone Recognition from Recorded Speech Using Non-Speech Segments”, Digital Signal Processing (to appear) Source Cell-Phone Recognition from Recorded Speech Using Non-Speech Segments |
Sách, tạp chí |
Tiêu đề: |
Source Cell-Phone Recognition from Recorded Speech Using Non-Speech Segments |
|
30. Ngo Hoang Huy, Nguyen Thi Thanh Mai, Bui Quang Trung, "Vietnamese text normalize and processing". Proceedings of National IT Conference. Nha Trang June. , 2002 |
Sách, tạp chí |
Tiêu đề: |
Vietnamese text normalize and processing |
|
32. Ngo Hoang Huy, Nguyen Thi Thanh Mai, Bui Quang Trung, "Vietnamese text normalize and processing". Proceedings of National IT Conference. Nha Trang June. , 2002 |
Sách, tạp chí |
Tiêu đề: |
Vietnamese text normalize and processing |
|
34. Hunt, A.; Black,A. và Alan, “Unit selection in a concatenative speech synthesis system using a large speech database,” Proc. in ICASSP Vol.1, tr. 373-376. LNAI 4274, pp. 87 – 94, Springer-Verlag, Berlin Heidelberg 2006 |
Sách, tạp chí |
Tiêu đề: |
Unit selection in a concatenative speech synthesis system using a large speech database |
|
43. Hansjoerg Mixdorf, Nguyen Tien Dung, Lưong Chi Mai, Ngo Hoang Huy “Quantitative Analysis and Synthesis of Syllabic Tones in Vietnamese,” Proc. in EUROSPEECH, Geneva, tr 177-180 |
Sách, tạp chí |
Tiêu đề: |
Quantitative Analysis and Synthesis of Syllabic Tones in Vietnamese |
|
44. Hansiorg Mixdorff, Nguyen Tien Dung, Vu Trung Nghia, “Duration Modeling in a Vietnamese Text To Speech System”, Speech Communication, 2005 |
Sách, tạp chí |
Tiêu đề: |
Duration Modeling in a Vietnamese Text To Speech System |
|
47. Trung-Nghia PHUNG, Thanh-Son PHAN, Thang Tat VU, Mai Chi LUONG and Masato AKAGI (2013), “Improving the naturalness of HMM-based TTStrained with limited data data by Temporal decomposition,” IEICE TRANS. INF. & SYST., Japan, Vol.E96(11), tr. 2417-2426 |
Sách, tạp chí |
Tiêu đề: |
Improving the naturalness of HMM-based TTStrained with limited data data by Temporal decomposition |
Tác giả: |
Trung-Nghia PHUNG, Thanh-Son PHAN, Thang Tat VU, Mai Chi LUONG and Masato AKAGI |
Năm: |
2013 |
|
tract length estimation for speaker normalization in speech recognition, VI Jornadas en Tecnología del Habla and II Iberian SLTech Workshop, FALA 2010, Vigo, Spain, 2010 |
Sách, tạp chí |
Tiêu đề: |
VI Jornadas en Tecnología del Habla and II Iberian SLTech Workshop |
Năm: |
2010 |
|
56. Silverman, K., Beckman, M., Pierrehumbert, J., Ostendorf, M., Wightman, C., Price, P. and Hirschberg, J., “ToBI: A Standard Scheme for Labeling Prosody”, in Proc. ICSLP 1992, 867-869 |
Sách, tạp chí |
Tiêu đề: |
ToBI: A Standard Scheme for Labeling Prosody |
|
59. Taylor, P., “Analysis and synthesis of intonation using the Tilt model”, J. Acoust. Soc. Am., 107: 1697-1714, 2000 |
Sách, tạp chí |
Tiêu đề: |
Analysis and synthesis of intonation using the Tilt model |
|
62. Vu Thang Tat; Luong, Mai Chi và Satoshi, Nakamura (2009), “An HMMbased Vietnamese Speech Synthesis System,” Proc. in Oriental COCOSDA, Urumqi, China, tr.116-121 |
Sách, tạp chí |
Tiêu đề: |
An HMMbased Vietnamese Speech Synthesis System |
Tác giả: |
Vu Thang Tat; Luong, Mai Chi và Satoshi, Nakamura |
Năm: |
2009 |
|
63. DO Van Thao, TRAN Do Dat, NGUYEN Thi Thu Trang “Nonuniformunit selection in Vietnamese Speech Synthesis,” Proceedings of the 2nd SoICT 2011, tr. 165-171 |
Sách, tạp chí |
Tiêu đề: |
Nonuniformunit selection in Vietnamese Speech Synthesis |
|
65. Nguyen Thi Thu Trang et al., “INTONATION ISSUES IN HMM-BASED SPEECH SYNTHESIS FOR VIETNAMESE,” SLTU-2014, St. Petersburg, Russia, 14-16 May 2014 |
Sách, tạp chí |
Tiêu đề: |
INTONATION ISSUES IN HMM-BASED SPEECH SYNTHESIS FOR VIETNAMESE |
|
71. Heiga Zen, Takashi Nose, Junichi Yamagishi, Shinji Sako, Takashi Masuko, AlanW. Black, Keiichi Tokuda. The HMM-basedSpeech Synthesis System (HTS) Version 2.0, 72. Puming Zhan and Alex Waibel, “Vocal tract length normalization for large vocabularycontinuous speech recognition”, Technical report, CMU-LTI-97-150, 1997 |
Sách, tạp chí |
Tiêu đề: |
Vocal tract length normalization for large vocabulary continuous speech recognition”", Technical report |
|