Enhancements of viterbi search for fast unit selection synthesis

The paper describes the optimisation of Viterbi search used in unit selection TTS, since with a large speech corpus necessary to achieve a high level of naturalness, the performance still suffers. To improve the search speed, the combination of sophisticated stopping schemes and pruning thresholds is employed into the baseline search. The optimised search is, moreover, extremely flexible in configuration, requiring only three intuitively comprehensible coefficients to be set. This provides the means for tuning the search depending on device resources, while it allows reaching significant performance increase. To illustrate it, several configuration scenarios, with speed

• Type: Journal
• Year: 2010
• Where: INTERSPEECH
• Authors: Daniel Tihelka, Jirí Kala, Jindrich Matousek
• Keywords: Baseline Search, INTERSPEECH 2010, Large Speech Corpus, Signal Processing, Unit Selection Tts