A survey on speech synthesis techniques in Indian languages

被引：11
作者：
Panda, Soumya Priyadarsini [1 ]
Nayak, Ajit Kumar [2 ]
Rai, Satyananda Champati [3 ]
机构：
[1] Silicon Inst Technol, Dept CSE, Bhubaneswar, Odisha, India
[2] Siksha O Anusandhan Univ, Dept CS & IT, Bhubaneswar, Odisha, India
[3] Silicon Inst Technol, Dept IT, Bhubaneswar, Odisha, India
来源：
MULTIMEDIA SYSTEMS | 2020年 / 26卷 / 04期
关键词：
Text to speech system; Speech synthesis; Indian languages; Concatenative synthesis; Formant synthesis; Articulatory synthesis; Syllable-based synthesis; HMM-based synthesis; Statistical parametric synthesis; Polyglot synthesis; Multilingual synthesis; Waveform concatenation; Deep learning; FORM CONCATENATION TECHNIQUE; SYNTHESIS SYSTEM; ARTICULATORY SYNTHESIS; TEXT; SELECTION; INTELLIGIBILITY; FEATURES; QUALITY; ENHANCEMENT; GENERATION;
D O I：
10.1007/s00530-020-00659-4
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
The text to speech technology has achieved significant progress during the past decade and is an active area of research and development in providing different human-computer interactive systems. Even though a number of speech synthesis models are available for different languages focusing on the domain requirements with many motive applications, a source of information on current trends in Indian language speech synthesis is unavailable till date making it difficult for the beginners to initiate research for the development of TTS systems for the low-resourced languages. This paper provides a review of the contributions made by different researchers in the field of Indian language speech synthesis along with a study on the Indian language characteristics and the associated challenges in designing TTS systems. A set of available applications and tools results out of different projects undertaken by different organizations along with a set of possible future developments are also discussed to provide a single reference to an important strand of research in speech synthesis which may benefit anyone interested to initiate research in this area.
引用
收藏
页码：453 / 478
页数：26
相关论文
共 178 条
[1]   Improved voicing decision using glottal activity features for statistical parametric speech synthesis [J].
Adiga, Nagaraj ;
Khonglah, Banriskhem K. ;
Prasanna, S. R. Mahadeva .
DIGITAL SIGNAL PROCESSING, 2017, 71 :131-143
[2]   Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers [J].
Akcay, Mehmet Berkehan ;
Oguz, Kaya .
SPEECH COMMUNICATION, 2020, 116 :56-76
[3]   A continuous vocoder for statistical parametric speech synthesis and its evaluation using an audio-visual phonetically annotated Arabic corpus [J].
Al-Radhi, Mohammed Salah ;
Abdo, Omnia ;
Csapo, Tamas Gabor ;
Abdou, Sherif ;
Nemeth, Geza ;
Fashal, Mervat .
COMPUTER SPEECH AND LANGUAGE, 2020, 60
[4]   Towards high-quality next-generation text-to-speech synthesis:: A multidomain approach by automatic domain classification [J].
Alias, Francesc ;
Sevillano, Xavier ;
Socoro, Joan Claudi ;
Gonzalvo, Xavier .
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2008, 16 (07) :1340-1354
[5]  
Alwan A., P URSI INT S SIGN SY, P367
[6]  
[Anonymous], 2007, SSW
[7]  
[Anonymous], P LIN AUD C KARLSR G
[8]  
Aryal Sandesh, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), P7694, DOI 10.1109/ICASSP.2014.6855097
[9]   Data driven articulatory synthesis with deep neural networks [J].
Aryal, Sandesh ;
Gutierrez-Osuna, Ricardo .
COMPUTER SPEECH AND LANGUAGE, 2016, 36 :260-273
[10]  
Aryal S, 2013, INT CONF ACOUST SPEE, P7952, DOI 10.1109/ICASSP.2013.6639213
12345678910