HMM Based Myanmar Text to Speech System

被引：0

作者：

Thu, Ye Kyaw ^{[1
]}

Pa, Win Pa ^{[2
]}

Ni, Jinfu ^{[3
]}

Shiga, Yoshinori ^{[3
]}

Finch, Andrew ^{[1
]}

Hori, Chiori ^{[3
]}

Kawai, Hisashi ^{[3
]}

Sumita, Eiichiro ^{[1
]}

机构：

[1] NICT, Multilingual Translat Lab, Kyoto, Japan

[2] UCSY, Nat Language Proc Lab, Yangon, Myanmar

[3] NICT, Spoken Language Commun Lab, Kyoto, Japan

来源：

16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5 | 2015年

关键词：

Speech Synthesis; Text to Speech (TTS); Hidden Markov Model (HMM); Ossian; Myanmar; GENERATION;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

This paper presents a complete statistical speech synthesizer for Myanmar which includes a syllable segmenter, text normalizer, grapheme-to-phoneme convertor, and an HMM-based speech synthesis engine. We believe this is the first such system for the Myanmar language. We performed a thorough human evaluation of the synthesizer relative to human and re-synthesized baselines. Our results show that our system is able to synthesize speech at a quality comparable with similar state-of-the-art synthesizers for other languages.

引用

页码：2237 / 2241

页数：5

共 50 条

[1] An HMM-based Mandarin Chinese Text-to-Speech system
Qian, Yao
Soong, Frank
Chen, Yining
Chu, Min
[J]. CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2006, 4274 : 223 - +
[2] An Isarn Dialect HMM-based Text-to-speech System
Janyoi, Pongsathon
Seresangtakul, Pusadee
[J]. 2017 2ND INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY (INCIT), 2017, : 1 - 6
[3] Myanmar Text-to-Speech System based on Tacotron-2
Win, Yuzana
Masada, Tomonari
[J]. 11TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE: DATA, NETWORK, AND AI IN THE AGE OF UNTACT (ICTC 2020), 2020, : 578 - 583
[4] Syllable based DNN-HMM Cantonese Speech-to-Text System
Wong, Timothy
Li, Claire W. Y.
Lam, Sam
Chiu, Billy
Lu, Qin
Li, Minglei
Xiong, Dan
Yu, Roy S.
Ng, Vincent T. Y.
[J]. LREC 2016 - TENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2016, : 3856 - 3862
[5] Myanmar text-to-speech system with rule-based tone synthesis
Win, Kyawt Yin
Takara, Tomio
[J]. ACOUSTICAL SCIENCE AND TECHNOLOGY, 2011, 32 (05) : 174 - 181
[6] A Speaker-Adaptive HMM-based Vietnamese Text-to-Speech System
Ninh, Duy Khanh
[J]. PROCEEDINGS OF 2019 11TH INTERNATIONAL CONFERENCE ON KNOWLEDGE AND SYSTEMS ENGINEERING (KSE 2019), 2019, : 342 - 346
[7] HMM-Based Finnish Text-to-Speech System Utilizing Glottal Inverse Filtering
Raitio, Tuomo
Suni, Antti
Pulakka, Hannu
Vainio, Martti
Alku, Paavo
[J]. INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 1881 - +
[8] The realization of speech recognition system based on HMM
Yiao, Mingming
[J]. 2008 PROCEEDINGS OF INFORMATION TECHNOLOGY AND ENVIRONMENTAL SYSTEM SCIENCES: ITESS 2008, VOL 4, 2008, : 24 - 29
[9] A Study on HMM based Speech Recognition System
Boruah, Saptarshi
Basishtha, Subhash
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND COMPUTING RESEARCH (ICCIC), 2013, : 153 - 157
[10] A Mongolian speech recognition system based on HMM
Gao, Guanglai
Biligetu
Nabuqing
Zhang, Shuwu
[J]. COMPUTATIONAL INTELLIGENCE, PT 2, PROCEEDINGS, 2006, 4114 : 667 - 676

← 1 2 3 4 5 →