Title :
Maximum Likelihood Based Temporal Frame Selection
Author :
Wu, Tingyao ; Van Compernolle, Dirk ; Duchateau, Jacques ; Van hamme, Hugo
Author_Institution :
Dept. of ESAT, Katholieke Univ.,, Leuven
Abstract :
In this paper, we propose a maximum likelihood (ML) based frame selection approach. A fixed frame rate adopted in most state-of-the-art speech recognition systems can face some problems, such as accidentally meeting noisy frames, assigning the same importance to each frame, and pitch asynchronous representation. As an attempt to avoid those problems, our approach selects reliable frames from a fine resolution along the time axis in a phoneme recognition task, we show that significant improvements are achieved with the frame selection approach comparing to a system with a fixed frame rate
Keywords :
maximum likelihood estimation; speech recognition; maximum likelihood; phoneme recognition task; pitch asynchronous representation; speech recognition systems; temporal frame selection; time axis; Decoding; Hidden Markov models; Humans; Maximum likelihood estimation; Power system harmonics; Speech recognition; Testing; Topology; Viterbi algorithm;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
Print_ISBN :
1-4244-0469-X
DOI :
10.1109/ICASSP.2006.1660029