Opens in a new tab

AES E-Library

← Back to search

Convention Paper

A Heuristic Text-Driven Approach for Applied Phoneme Alignment

Authors: Avdelidis, Konstantinos; Dimoulas, Charalampos; Kalliris, George; Papanikolaou, George

AES Convention 128 · Paper 8134 · May 2010

Abstract

The paper introduces a phoneme matching algorithm considering a novel concept of functional strategy. In contrast to the classic methodologies which are focusing on the convergence to a fixed expected phonemic sequence (EPS), the presented method follows a more realistic approach. Based on text input, a soft EPS is populated taking into consideration the structural and linguistic deviations which may appear in a naturally spoken sequence. The results of the matching process is evaluated using fuzzy inference and is consisted of both the phoneme transition positions as well as the actual utterance phonemic content. An overview of the algorithm focusing in the reduction of the computational cost is presented.

Details

Published in
AES Convention 128
AES Convention
128
Paper number
8134
Publication date
May 6, 2010
Session subject
Audio Processing—Music and Speech Signal Processing
Affiliation
Aristotle University of Thessaloniki, Thessaloniki, Greece (See document for exact affiliation information.)
Type
Convention Paper