Building speech synthesis systems for Indian languages

Pradhan, Abhijit; Prakash, Anusha; Shanmugam, S. Aswin; Kasthuri, G. R.; Krishnan, R.; Murthy, Hema A.

doi:10.1109/ncc.2015.7084931

Cited by 10 publications

(4 citation statements)

References 16 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Syllabicationisthefirstprocessindevelopingspeechsystems,particularlytext-to-speech(TTS), whichsupportsthenaturalnessandintelligibilityoftheTTSsystem (Ramlietal.,2015).Hence, propersyllabicationisnecessaryparticularlyinshowingvariousfeaturesofthelanguage'sarticulation and pronunciation as syllable-based synthesizers produce more speech synthesis (Pradhan et al, 2015).Somesyllabicationprocessesarethroughtherule-basedapproach,althoughthereareother approachestosegmentingthewords.…”

Section: The Syllabication Processmentioning

confidence: 99%

Rules for Orthographic Word Parsing of the Philippines' Cebuano-Visayan Language Using Context-Free Grammars

Caroro

Paredes

Lumasag

2020

International Journal of Software Science and Computational Intelligence

View full text Add to dashboard Cite

Syllabication is essential in the preprocessing stage of speech systems. In the context of the Philippines' Cebuano-Visayan language's syllabication rules, the existing rules do not include hyphenated words although the hyphen defines the syllable boundary in a word. Hence, this study created grammar rules for hyphenated words which include sequences of a hyphen between vowel-consonant, consonant-consonant, vowel-vowel, and consonant-vowel. The test was done for the enhanced grammar rules for Cebuano-Visayan syllabication with 1,465 representative hyphenated and non-hyphenated words of varying lengths. The result further implies that the syllabication analysis for hyphenated words showed that hyphens improve the naturalness and intelligibility in the utterance of the words, thereby enhancing the understanding and comprehension of the Cebuano-Visayan discourse.

show abstract

Section: The Syllabication Processmentioning

confidence: 99%

Rules for Orthographic Word Parsing of the Philippines' Cebuano-Visayan Language Using Context-Free Grammars

Caroro

Paredes

Lumasag

2020

International Journal of Software Science and Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Accurate segmentation is required for text to speech synthesis systems. Automatic segmentation using statistical approaches leads to poor boundary information when small training data is used whereas manual segmentation leads to human errors (Pradhan et al, 2015).…”

Section: Figure 1: Overview Of Text To Speech Synthesis Text Preprocessingmentioning

confidence: 99%

“…The basic units of the Indian language writing system called 'Aksharas'(Letters), orthographically represent a speech sound, are syllabic in nature. All Indian languages consist of 15-18 vowels and 35-38 consonants (Pradhan et al, 2015). The most frequently occurring syllables hardly exceed 300 for each language.…”

Section: Tts Development For Indian Languagesmentioning

confidence: 99%

Recent Trends in Text to Speech Synthesis of Indian Languages

Joshi¹,

Bairagi²

2019

helix

View full text Add to dashboard Cite

A Text To Speech (TTS) synthesizer is a computer application capable of converting arbitrary input text into speech. This conversion broadly involves two steps, namely, text processing and speech synthesis. Text processing converts the entered text to a sequence of synthesis units, while speech synthesis is the generation of an acoustic wave form corresponding to each of these units. Naturalness and intelligibility are the most important qualities expected from a TTS system. In this paper we aim to provide an overview of various techniques for text to speech synthesis, discuss their characteristics, summarize and compares advantages and drawbacks. We have listed various Text-to-Speech synthesis frameworks developed and implemented at different Indian institutes.

show abstract

“…Using a limited set of suffix units within the proposed hybrid approach, significant improvements in the quality of the SSS system is obtained without requiring additional data collection or careful tuning of the system. Syllable-based speech synthesis has been successful both in unit selection and HMM-based systems [13]. However, suffixes in Turkish are not necessarily syllables.…”

Section: Introductionmentioning

confidence: 99%

Hybrid statistical/unit-selection Turkish speech synthesis using suffix units

Demiroğlu

Guner

2016

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Unit selection based text-to-speech synthesis (TTS) has been the dominant TTS approach of the last decade. Despite its success, unit selection approach has its disadvantages. One of the most significant disadvantages is the sudden discontinuities in speech that distract the listeners (Speech Commun 51:1039-1064). The second disadvantage is that significant expertise and large amounts of data is needed for building a high-quality synthesis system which is costly and time-consuming. The statistical speech synthesis (SSS) approach is a promising alternative synthesis technique. Not only that the spurious errors that are observed in the unit selection system are mostly not observed in SSS but also building voice models is far less expensive and faster compared to the unit selection system. However, the resulting speech is typically not as natural-sounding as speech that is synthesized with a high-quality unit selection system. There are hybrid methods that attempt to take advantage of both SSS and unit selection systems. However, existing hybrid methods still require development of a high-quality unit selection system. Here, we propose a novel hybrid statistical/unit selection system for Turkish that aims at improving the quality of the baseline SSS system by improving the prosodic parameters such as intonation and stress. Commonly occurring suffixes in Turkish are stored in the unit selection database and used in the proposed system. As opposed to existing hybrid systems, the proposed system was developed without building a complete unit selection synthesis system. Therefore, the proposed method can be used without collecting large amounts of data or utilizing substantial expertise or time-consuming tuning that is typically required in building unit selection systems. Listeners preferred the hybrid system over the baseline system in the AB preference tests.

show abstract

Building speech synthesis systems for Indian languages

Cited by 10 publications

References 16 publications

Rules for Orthographic Word Parsing of the Philippines' Cebuano-Visayan Language Using Context-Free Grammars

Rules for Orthographic Word Parsing of the Philippines' Cebuano-Visayan Language Using Context-Free Grammars

Recent Trends in Text to Speech Synthesis of Indian Languages

Hybrid statistical/unit-selection Turkish speech synthesis using suffix units

Contact Info

Product

Resources

About