DATA-DRIVEN PHRASING FOR SPEECH SYNTHESIS IN LOW-RESOURCE LANGUAGES

被引：0
|
作者：
Parlikar, Alok [1 ]
Black, Alan W. [1 ]
机构：
[1] Carnegie Mellon Univ, Language Technol Inst, Pittsburgh, PA 15213 USA
来源：
2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2012年
关键词：
Speech Synthesis; Phrase Break Prediction; Low Resource Languages;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
We present an approach to build phrase break prediction models when synthesizing text in low resource languages. This method allows building models without depending on the availability of part of speech taggers, or corpus with hand annotated breaks. We use the same speech data used for building a synthetic voice, to deduce acoustic phrase breaks. We perform unsupervised part of speech induction over a small text corpus in the language at hand. We use these tags and train a grammar based phrasing model. In this paper, we show results for the languages: English, Portuguese and Marathi, which suggest that we can quickly build very reasonable phrasing models for new languages using very little data.
引用
收藏
页码：4013 / 4016
页数：4
相关论文
共 50 条
  • [1] USING SPEECH ENHANCEMENT TO REALIZE SPEECH SYNTHESIS OF LOW-RESOURCE DUNGAN LANGUAGES
    Jiang, Rui
    Chen, Chengsi
    Shan, Xin
    Yang, Hongwu
    [J]. 2021 24TH CONFERENCE OF THE ORIENTAL COCOSDA INTERNATIONAL COMMITTEE FOR THE CO-ORDINATION AND STANDARDISATION OF SPEECH DATABASES AND ASSESSMENT TECHNIQUES (O-COCOSDA), 2021, : 193 - 198
  • [2] Crowdsourcing Speech Data for Low-Resource Languages from Low-IncomeWorkers
    Abraham, Basil
    Goel, Danish
    Siddarth, Divya
    Bali, Kalika
    Chopra, Manu
    Choudhury, Monojit
    Joshi, Pratik
    Jyoti, Preethi
    Sitaram, Sunayana
    Seshadri, Vivek
    [J]. PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2020), 2020, : 2819 - 2826
  • [3] The Usefulness of Imperfect Speech Data for ASR Development in Low-Resource Languages
    Badenhorst, Jaco
    de Wet, Febe
    [J]. INFORMATION, 2019, 10 (09)
  • [4] Low-Resource Footprint, Data-Driven Malware Detection on Android
    Aonzo, Simone
    Merlo, Alessio
    Migliardi, Mauro
    Oneto, Luca
    Palmieri, Francesco
    [J]. IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING, 2020, 5 (02): : 213 - 222
  • [5] AUTOMATIC RATING OF SPONTANEOUS SPEECH FOR LOW-RESOURCE LANGUAGES
    Al-Ghezi, Ragheb
    Getman, Yaroslav
    Voskoboinik, Ekaterina
    Singh, Mittul
    Kurimo, Mikko
    [J]. 2022 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP, SLT, 2022, : 339 - 345
  • [6] Speech recognition datasets for low-resource Congolese languages
    Kimanuka, Ussen
    Maina, Ciira wa
    Buyuk, Osman
    [J]. DATA IN BRIEF, 2024, 52
  • [7] Linguistic Foundations of Low-Resource Languages for Speech Synthesis on the Example of the Kazakh Language
    Bekmanova, Gulmira
    Yergesh, Banu
    Sharipbay, Altynbek
    Omarbekova, Assel
    Zakirova, Alma
    [J]. COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2022 WORKSHOPS, PART III, 2022, 13379 : 3 - 14
  • [8] Efficient neural speech synthesis for low-resource languages through multilingual modeling
    de Korte, Marcel
    Kim, Jaebok
    Klabbers, Esther
    [J]. INTERSPEECH 2020, 2020, : 2967 - 2971
  • [9] Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation
    Liu, Zoey
    Prud'hommeaux, Emily
    [J]. TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2022, 10 : 393 - 413
  • [10] Tackling Hate Speech in Low-resource Languages with Context Experts
    Nkemelu, Daniel
    Shah, Harshil
    Essa, Irfan
    Best, Michael L.
    [J]. PROCEEDINGS OF THE 2022 INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES AND DEVELOPMENT, ICTD 2022, 2022,
12345