Open Access
Text processing for text-to-speech systems in Indian languages.
Anand Arokia Raj,Tanuja Sarkar,Sathish Pammi,Santhosh Yuvaraj,Mohit Bansal,Kishore Prahallad,Alan W. Black +6 more
- pp 188-193
Reads0
Chats0
TLDR
The efforts in addressing the issues of Font-to-Akshara mapping, pronunciation rules for Aksharas, text normalization in the context of building text- to-speech systems in Indian languages are discussed.Abstract:
To build a natural sounding speech synthesis system, it is essential that the text processing component produce an appropriate sequence of phonemic units corresponding to an arbitrary input text. In this paper we discuss our efforts in addressing the issues of Font-to-Akshara mapping, pronunciation rules for Aksharas, text normalization in the context of building text-to-speech systems in Indian languages.read more
Citations
More filters
Proceedings Article
The IIIT-H Indic Speech Databases.
TL;DR: This paper discusses the efforts in collecting speech databases for Indian languages – Bengali, Hindi, Kannada, Malayalam, Marathi, Tamil and Telugu, and discusses relevant design considerations in collecting these databases.
Journal ArticleDOI
Curriculum learning based approach for noise robust language identification using DNN with attention
TL;DR: In comparison to multi-SNR models, the LID systems trained with curriculum learning have performed better in terms of equal error rate (EER) and generalization in EER across varying background environments.
Proceedings ArticleDOI
Random forests for statistical speech synthesis.
TL;DR: Improvements equivalent to more than doubling the data can be achieved, offering end users significantly better synthesis from the same data size, particularly with voices with only 30 minutes of speech.
Text normalization system for Bangla
TL;DR: This paper describes a process of text normalization system of Bangla language (exonym: Bengali) by identifying the semiotic classes from Bangla text corpus and a set of rules were written for tokenization and verbalization.
Journal ArticleDOI
An Improved Syllabification for a Better Malay Language Text-to-Speech Synthesis (TTS)
TL;DR: Investigations of previous syllabification technique of Malay language to identify the limitations are investigated and an improved syllabify technique is proposed and compared against the performance of another three known syllabifications.
References
More filters
Journal ArticleDOI
Statistical Parametric Speech Synthesis
TL;DR: This paper gives a general overview of techniques in statistical parametric speech synthesis, and contrasts these techniques with the more conventional unit selection technology that has dominated speech synthesis over the last ten years.
Proceedings ArticleDOI
Unit selection in a concatenative speech synthesis system using a large speech database
Andrew Hunt,Alan W. Black +1 more
TL;DR: In this paper, a state transition network is proposed to select and concatenate phonemes from a large speech database to produce a natural realisation of a target phoneme sequence predicted from text which is annotated with prosodic and phonetic context information.
The HMM-based speech synthesis system (HTS) version 2.0.
Heiga Zen,Takashi Nose,Junichi Yamagishi,Shinji Sako,Takashi Masuko,Alan W. Black,Keiichi Tokuda +6 more
TL;DR: This paper describes HTS version 2.0 in detail, as well as future release plans, which include a number of new features which are useful for both speech synthesis researchers and developers.
Journal ArticleDOI
Normalization of non-standard words
Richard Sproat,Alan W. Black,Stanley F. Chen,Shankar Kumar,Mari Ostendorf,Christopher D. Richards +5 more
TL;DR: A taxonomy of NSWs was developed on the basis of four rather distinct text types, and several general techniques including n-gram language models, decision trees and weighted finite-state transducers were investigated, demonstrating that a systematic treatment can lead to better results than have been obtained by the ad hoc treatments that have typically been used in the past.