Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10370352 | Speech Communication | 2013 | 14 Pages |
Abstract
⺠Mixed style speech causes problems when training acoustic models for speech applications, such as speaker ID and ASR. ⺠This study is a first attempt for speaker clustering under mixed speaking styles which include reading and singing. ⺠Two types of subspace learning strategies in the GMM mean supervector space are studied: unsupervised and supervised. ⺠Advanced clustering algorithms are evaluated on a database that includes reading and singing the lyrics for each speaker. ⺠LPP subspace learning and a proposed cluster refining based on PLDA significantly improves clustering accuracies.
Related Topics
Physical Sciences and Engineering
Computer Science
Signal Processing
Authors
Mahnoosh Mehrabani, John H.L. Hansen,