The Community for Technology Leaders
Green Image
ABSTRACT
This work presents an unsupervised speaker change detection algorithm based on support vector machines (SVM) to detect speaker change (SC) in a speech stream. The proposed algorithm is called the SVM training misclassification rate (STMR). The STMR can identify SCs with less speech data collection, making it capable of detecting speaker segments with short duration. According to experiments on the NIST Rich Transcription 2005 Spring Evaluation (RT-05S) corpus, the STMR has a missed detection rate of only 19.67 percent.
INDEX TERMS
Microphones, Hidden Markov models, Support vector machines, Acoustics, Speech recognition, Density estimation robust algorithm, Training,Speaker segmentation, Support Vector Machine, Speaker Change Detection
CITATION
"Unsupervised speaker change detection using SVM training misclassification rate", IEEE Transactions on Computers, vol. 56, no. , pp. 1234-1244, September 2007, doi:10.1109/TC.2007.70746
95 ms
(Ver 3.3 (11022016))