Review: Speaker segmentation and clustering
Signal Processing
Unfolding speaker clustering potential: a biomimetic approach
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Robust detection of phone boundaries using model selection criteria with few observations
IEEE Transactions on Audio, Speech, and Language Processing
Speaker diarization exploiting the eigengap criterion and cluster ensembles
IEEE Transactions on Audio, Speech, and Language Processing
Speaker diarization using low-cost wearable wireless sensors
Proceedings of the 3rd International Conference on Information and Communication Systems
A review on speaker diarization systems and approaches
Speech Communication
Hi-index | 0.00 |
An algorithm for automatic speaker segmentation based on the Bayesian information criterion (BIC) is presented. BIC tests are not performed for every window shift, as previously, but when a speaker change is most probable to occur. This is done by estimating the next probable change point thanks to a model of utterance durations. It is found that the inverse Gaussian fits best the distribution of utterance durations. As a result, less BIC tests are needed, making the proposed system less computationally demanding in time and memory, and considerably more efficient with respect to missed speaker change points. A feature selection algorithm based on branch and bound search strategy is applied in order to identify the most efficient features for speaker segmentation. Furthermore, a new theoretical formulation of BIC is derived by applying centering and simultaneous diagonalization. This formulation is considerably more computationally efficient than the standard BIC, when the covariance matrices are estimated by other estimators than the usual maximum-likelihood ones. Two commonly used pairs of figures of merit are employed and their relationship is established. Computational efficiency is achieved through the speaker utterance modeling, whereas robustness is achieved by feature selection and application of BIC tests at appropriately selected time instants. Experimental results indicate that the proposed modifications yield a superior performance compared to existing approaches.