Unsupervised speaker segmentation with residual phase and MFCC features
Expert Systems with Applications: An International Journal
IEEE Transactions on Audio, Speech, and Language Processing
Hi-index | 14.98 |
This work presents an unsupervised speaker change detection algorithm based on support vector machine (SVM) to detect speaker change in a speech stream. The proposed algorithm is called the SVM training misclassification rate (STMR). The STMR can identify speaker changes 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%.