Enhancing automatically discovered multi-level acoustic patterns considering context consistency with applications in spoken term detection
Journal
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Journal Volume
2015-August
Pages
5231-5235
Date Issued
2015
Author(s)
Abstract
This paper presents a novel approach for enhancing the multiple sets of acoustic patterns automatically discovered from a given corpus. In a previous work it was proposed that different HMM configurations (number of states per model, number of distinct models) for the acoustic patterns form a two-dimensional space. Multiple sets of acoustic patterns automatically discovered with the HMM configurations properly located on different points over this two-dimensional space were shown to be complementary to one another, jointly capturing the characteristics of the given corpus. By representing the given corpus as sequences of acoustic patterns on different HMM sets, the pattern indices in these sequences can be relabeled considering the context consistency across the different sequences. Good improvements were observed in preliminary experiments of pattern spoken term detection (STD) performed on both TIMIT and Mandarin Broadcast News with such enhanced patterns. © 2015 IEEE.
Event(s)
40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Subjects
acoustic patterns; hidden Markov models; spoken term detection; unsupervised learning; zero-resourced speech recognition
Other Subjects
Audio signal processing; Speech communication; Speech recognition; Unsupervised learning; Broadcast news; Multilevels; Multiple set; Number of state; Pattern index; Spoken Term Detection (STD); Spoken term detections; Two dimensional spaces; Hidden Markov models
Type
conference paper