| Paper: | SP-P2.10 | ||
| Session: | Speaker Adaptation | ||
| Time: | Tuesday, May 18, 13:00 - 15:00 | ||
| Presentation: | Poster | ||
| Topic: | Speech Processing: Adaptation/Normalization | ||
| Title: | EIGEN-MLLRS APPLIED TO UNSUPERVISED SPEAKER ENROLLMENT FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION | ||
| Authors: | Xavier Aubert; Philips Research Laboratories Aachen | ||
| Abstract: | The concept of Eigen-MLLRs, a variant of the Eigen-Voice method, is applied to unsupervised speaker enrollment in a large vocabulary CSR system. The emphasis is on fast adaptation. Two ways of estimating multiple Eigen-MLLR transformations are introduced, either joint or separated with respect to the Eigen-MLLR vector space. The first case allows multiple transforms to be robustly estimated from sparse data while the second achieves more accurate adaptation when more samplesbecome available. The first decoded words spoken by a new test speaker are used to adapt the speaker-independent HMM means. The impact of this new enrollment algorithm is evaluated over a large real-life database dealing with professional medical transcriptions. Significant reductions of word-error-rates are achieved with less than 10 seconds of enrollment speech and without any supervision. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops