KNNDIST: A non-parametric distance measure for speaker segmentation

Mohammadi, S. H ; Sharif University of Technology | 2012

491 Viewed
  1. Type of Document: Article
  2. Publisher: 2012
  3. Abstract:
  4. A novel distance measure for distance-based speaker segmentation is proposed. This distance measure is nonparametric, in contrast to common distance measures used in speaker segmentation systems, which often assume a Gaussian distribution when measuring the distance between two audio segments. This distance measure is essentially a k-nearest-neighbor distance measure. Non-vowel segment removal in preprocessing stage is also proposed. Speaker segmentation performance is tested on artificially created conversations from the TIMIT database and two AMI conversations. For short window lengths, Missed Detection Rated is decreased significantly. For moderate window lengths, a decrease in both Missed Detection and False Alarm Rates occur. The computational cost of the distance measure is high for long window lengths
  5. Keywords:
  6. Distance measure ; K-nearest-neighbor ; Speaker segmentation ; Computational costs ; Distance measure ; Distance-based ; False alarm rate ; K-nearest neighbors ; Missed detections ; Speaker segmentations ; Timit database ; Computer applications ; Computer simulation ; Audio systems
  7. Source: 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 ; Volume 3 , 2012 , Pages 2279-2282 ; 9781622767595 (ISBN)
  8. URL: http://www.isca-speech.org/archive/interspeech_2012/i12_2282.html
  9. URL: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=