3 |
Phone adaptive training for speaker diarization
|
|
|
|
In: INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association, September 9-13, Portland, Oregon, USA ; INTERSPEECH 2012 ; https://hal.archives-ouvertes.fr/hal-00733385 ; INTERSPEECH 2012, Sep 2012, Portland, U.S. Outlying Islands. pp.1 (2012)
|
|
Abstract:
International audience ; The linguistic content of a speech signal is a source of unwanted variation which can degrade speaker diarization performance. This paper presents our latest work to reduce its impact. The new approach, referred to as Phone Adaptive Training (PAT), is analogous to speaker adaptive training used in automatic speech recognition. We report an oracle experiment which shows that PAT has the potential to deliver a 33% relative improvement in the diarization error rate of our baseline system. Practical experiments show significant improvements across two standard, independent evaluation datasets.
|
|
Keyword:
[INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM]; Phone Adaptive Training; Speaker Diarization; Speaker Discrimination
|
|
URL: https://hal.archives-ouvertes.fr/hal-00733385/document https://hal.archives-ouvertes.fr/hal-00733385 https://hal.archives-ouvertes.fr/hal-00733385/file/Phone_Adaptive_Training_for_Speaker_Diarization_7_1_.pdf
|
|
BASE
|
|
Hide details
|
|
|
|