Continuity Metric for Unit Selection based Text-to-Speech Synthesis

Lakkavalli, Vikram Ramesh and Arulmozhi, P and Ramakrishnan, AG (2010) Continuity Metric for Unit Selection based Text-to-Speech Synthesis. In: International Conference on Signal Processing and Communications, JUL 18-21, 2010, Indian Inst Sci, Bangalore, INDIA.

PDF Continuity.pdf - Published Version Restricted to Registered users only Download (192kB) | Request a copy

Abstract

A new method based on unit continuity metric (UCM) is proposed for optimal unit selection in text-to-speech (TTS) synthesis. UCM employs two features, namely, pitch continuity metric and spectral continuity metric. The methods have been implemented and tested on our test bed called MILE-TTS and it is available as web demo. After verification by a self selection test, the algorithms are evaluated on 8 paragraphs each for Kannada and Tamil by native users of the languages. Mean-opinion-score (MOS) shows that naturalness and comprehension are better with UCM based algorithm than the non-UCM based ones. The naturalness of the TTS output is further enhanced by a new rule based algorithm for pause prediction for Tamil language. The pauses between the words are predicted based on parts-of-speech information obtained from the input text.

Item Type:	Conference Paper
Publisher:	IEEE
Additional Information:	Copyright 2010 IEEE. Personal use of this material is permitted.However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Keywords:	unit selection; MFCC; unit continuity metric; pitch continuity metric; spectral continuity metric; MILE-TTS; part-of-speech; pause model; Tamil; Kannada
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	31 Mar 2011 09:24
Last Modified:	31 Mar 2011 09:24
URI:	http://eprints.iisc.ac.in/id/eprint/36372

Actions (login required)

View Item