Logo
Indic TTS
Common Label Set
All the sounds or phonemes of 22 Indian languages are listed. Similar sounds across different languages are mapped together and denoted by a single label. These labels are represented using the Roman alphabet set. Since the number of sounds in a language exceeds the number of roman characters, certain suffixes are used. Suffix x is used to denote retroflex place of articulation, for eg: /d/ vs /dx/. For aspiration, suffix h is used, for, eg: /g/ vs /gh/. Certain sounds are language-specific. They are represented by separate labels. /zh/ is predominant in Tamil and Malayalam. Certain phonemes in Hindi like /kq/, /khq/ have been added to account for some pronunciations in foreign languages. Marathi has both dental and palatal affricates (/c/, /cx/, /j/, /jx/) compared to other languages which have only palatal affricates (/c/, /j/). Some languages have both phoneme and grapheme representations; this is to ensure that the native script is largely recoverable from the transliterated text. The International Phonetic Alphabet (IPA) symbols are used as references.
Related Work
A Common Attribute based Unified HTS framework for Speech Synthesis in Indian Languages
Logo
Indic TTS
Indic TTS : Enhancing text-to-speech (TTS) synthesis for Indian languages, optimizing quality and integrating compact TTS into disability aids and diverse applications.
Home
About
People
Publications
Demo
Audio Samples
Contact Us
© Copyright 2023, Speech Technology Consortium,
Bhashini, MeiTY and by Hema A Murthy & S Umesh,
Department Of Computer Science and Engineering and Electrical Engineering, IIT MADRAS. All Rights Reserved
Maintained by NetPhenix IT Solutions.