Unsupervised spoken term detection with spoken queries by multi-level acoustic patterns with varying model granularity
Journal
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages
7814-7818
Date Issued
2014
Author(s)
Abstract
This paper presents a new approach for unsupervised Spoken Term Detection with spoken queries using multiple sets of acoustic patterns automatically discovered from the target corpus. The different pattern HMM configurations(number of states per model, number of distinct models, number of Gaussians per state)form a three-dimensional model granularity space. Different sets of acoustic patterns automatically discovered on different points properly distributed over this three-dimensional space are complementary to one another, thus can jointly capture the characteristics of the spoken terms. By representing the spoken content and spoken query as sequences of acoustic patterns, a series of approaches for matching the pattern index sequences while considering the signal variations are developed. In this way, not only the on-line computation load can be reduced, but the signal distributions caused by different speakers and acoustic conditions can be reasonably taken care of. The results indicate that this approach significantly outperformed the unsupervised feature-based DTW baseline by 16.16% in mean average precision on the TIMIT corpus. © 2014 IEEE.
Event(s)
2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
Subjects
dynamic time warping; hidden Markov models; spoken term detection; unsupervised learning; zero resource speech recognition
SDGs
Other Subjects
Hidden Markov models; Speech recognition; Unsupervised learning; Acoustic conditions; Dynamic time warping; Online computations; Signal distribution; Signal variations; Spoken term detections; Three dimensional space; Three-dimensional model; Signal processing
Type
conference paper