Robust HMM-Based Speech/Music Segmentation

In this paper we present a new approach towards high performance speech/music segmentation on realistic tasks related to the automatic transcription of broadcast news. In the approach presented here, the local probability density function (PDF) estimators trained on clean microphone speech are used as a channel model at the output of which the entropy and ``dynamism'' will be measured and integrated over time through a 2-state (speech and and non-speech) hidden Markov model (HMM) with minimum duration constraints. The parameters of the HMM are trained using the EM algorithm in a completely unsupervised manner. Different experiments, including a variety of speech and music styles, as well as different segment durations of speech and music signals (real data distribution, mostly speech, or mostly music), will illustrate the robustness of the approach, which in each case achieves a frame-level accuracy greater than 94\%.


Published in:
ICASSP, 1746-1749
Presented at:
ICASSP
Year:
2002
Publisher:
Orlando, Florida
Keywords:
Note:
IDIAP-RR 01-33
Laboratories:




 Record created 2006-03-10, last modified 2018-03-17

n/a:
Download fulltextPDF
External links:
Download fulltextURL
Download fulltextRelated documents
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)