Soft Counting Poisson Mixture Model-Based Polling Method for Speech/Nonspeech Classification

Youngjoo SUH
Hoirin KIM
Minsoo HAHN
Yongju LEE

IEICE TRANSACTIONS on Information and Systems   Vol.E89-D    No.12    pp.2994-2997
Publication Date: 2006/12/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e89-d.12.2994
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Speech and Hearing
speech/nonspeech classification,  soft counting,  Poisson polling,  

Full Text: PDF(145.3KB)>>
Buy this Article

In this letter, a new segment-level speech/nonspeech classification method based on the Poisson polling technique is proposed. The proposed method makes two modifications from the baseline Poisson polling method to further improve the classification accuracy. One of them is to employ Poisson mixture models to more accurately represent various segmental patterns of the observed frequencies for frame-level input features. The other is the soft counting-based frequency estimation to improve the reliability of the observed frequencies. The effectiveness of the proposed method is confirmed by the experimental results showing the maximum error reduction of 39% compared to the segmentally accumulated log-likelihood ratio-based method.

open access publishing via