A Unified Parser for Developing Indian Language Text to Speech Synthesizers

Baby, Arun; Nishanthi, N L; Thomas, Anju Leela; Murthy, Hema A.

doi:10.1007/978-3-319-45510-5_59

Cited by 28 publications

(32 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CLS provides a standard notation of phones across different Indian languages in Latin-1 script. A unified parser is used to convert words in Indian languages to CLS representation [15].…”

Section: Phone Representation: Common Label Set (Cls)mentioning

confidence: 99%

See 1 more Smart Citation

Building Multilingual End-to-End Speech Synthesisers for Indian Languages

Prakash¹,

Thomas²,

Umesh³

et al. 2019

10th ISCA Workshop on Speech Synthesis (SSW 10)

View full text Add to dashboard Cite

Building text-to-speech (TTS) synthesisers is a difficult task, especially for low resource languages. Language-specific modules need to be developed for system building. End-to-end speech synthesis has become a popular paradigm as a TTS can be trained using only pairs. However, end-to-end speech synthesis is not scalable in a multilanguage scenario, as the vocabulary increases with the number of different scripts. In this paper, TTSes are trained for Indian languages using two text representations-character-based and phone-based. For the character-based approach, a multi-language character map (MLCM) is proposed to easily train Indic speech synthesisers. The phone-based approach uses the common label set (CLS) representation for Indian languages. Both approaches leverage the similarities that exist among the languages. The advantage is a compact representation across multiple languages. Experiments are conducted by building TTSes using monolingual data and by pooling data across two languages. The ability to synthesise code-mixed text using the phone-based approach is also assessed. Subjective evaluations indicate that reasonably good quality Indic TTSes can be developed using both approaches. This emphasises the need to incorporate multilingual text processing in the end-to-end framework.

show abstract

“…CLS provides a standard notation of phones across different Indian languages in Latin-1 script. A unified parser is used to convert words in Indian languages to CLS representation [15].…”

Section: Phone Representation: Common Label Set (Cls)mentioning

confidence: 99%

“…To obtain the phone-based representation from the input text, the unified parser for Indian languages is used [15]. Phones are represented in terms of common label set (CLS) notations [6].…”

Section: Introductionmentioning

confidence: 99%

Building Multilingual End-to-End Speech Synthesisers for Indian Languages

Prakash¹,

Thomas²,

Umesh³

et al. 2019

10th ISCA Workshop on Speech Synthesis (SSW 10)

View full text Add to dashboard Cite

show abstract

“…An overview of obtaining the phone and syllable sequences of a multilingual (or monolingual) text is illustrated in Figure 1. To parse Indic words, the unified parser is used [22]. The unified parser is a languageindependent parser for Indian languages that uses a set of pre-defined rules to convert Indic words to corresponding syllable and phone sequences.…”

Section: Parsing Words In a Multilingual Textmentioning

confidence: 99%

Code-switching in Indic Speech Synthesisers

et al. 2018

Self Cite

View full text Add to dashboard Cite

Most Indians are inherently bilingual or multilingual owing to the diverse linguistic culture in India. As a result, code-switching is quite common in conversational speech. The objective of this work is to train good quality text-to-speech (TTS) synthesisers that can seamlessly handle code-switching. To achieve this, bilingual TTSes that are capable of handling phonotactic variations across languages are trained using combinations of monolingual data in a unified framework. In addition to segmenting Indic speech data using signal processing cues in tandem with hidden Markov model-deep neural network (HMM-DNN), we propose to segment Indian English data using the same approach after NIST syllabification. Then, bilingual HTS-STRAIGHT based systems are trained by randomizing the order of data so that the systematic interactions between the two languages are captured better. Experiments are conducted by considering three language pairs: Hindi+English, Tamil+English and Hindi+Tamil. The code-switched systems are evaluated on monolingual, code-mixed and code-switched texts. Degradation mean opinion score (DMOS) for monolingual sentences shows marginal degradation over that of an equivalent monolingual TTS system, while the DMOS for bilingual sentences is significantly better than that of the corresponding monolingual TTS systems.

show abstract

“…For each language, we released two pronunciation lexicons created using the Festvox Indic frontend [9], which used a phoneset similar to SAMPA and IIT Madras' Common Label Set [10] which used an IPA-based phoneset. Both these phonesets were created for Indian languages and facilitated phoneme sharing between the three languages.…”

Section: Pronunciation Lexiconsmentioning

confidence: 99%

Interspeech 2018 Low Resource Automatic Speech Recognition Challenge for Indian Languages

Srivastava¹,

Sitaram²,

Mehta³

et al. 2018

6th Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2018)

View full text Add to dashboard Cite

India has more than 1500 1 languages, with 30 of them spoken by more than one million native speakers. Most of them are low-resource and could greatly benefit from speech and language technologies. Building speech recognition support for these low-resource languages requires innovation in handling constraints on data size, while also exploiting the unique properties and similarities among Indian languages. With this goal, we organized a low-resource Automatic Speech Recognition challenge for Indian languages as part of Interspeech 2018. We released 50 hours of speech data with transcriptions for Tamil, Telugu and Gujarati, amounting to a total of 150 hours. Participants were required to only use the data we released for the challenge to preserve the low-resource setting, however, they were not restricted to work on any particular aspect of the speech recognizer. We received 109 submissions from 18 research groups and evaluated the systems in terms of Word Error Rate on a blind test set. In this paper we summarize the data, approaches and results of the challenge.

show abstract

A Unified Parser for Developing Indian Language Text to Speech Synthesizers

Cited by 28 publications

References 5 publications

Building Multilingual End-to-End Speech Synthesisers for Indian Languages

Building Multilingual End-to-End Speech Synthesisers for Indian Languages

Code-switching in Indic Speech Synthesisers

Interspeech 2018 Low Resource Automatic Speech Recognition Challenge for Indian Languages

Contact Info

Product

Resources

About