| Paper: | SP-P16.10 | ||
| Session: | Speech Modeling for Robust Speech Recognition | ||
| Time: | Friday, May 21, 15:30 - 17:30 | ||
| Presentation: | Poster | ||
| Topic: | Speech Processing: Robust Speech Recognition | ||
| Title: | MINIMUM KULLBACK-LEIBLER DISTANCE BASED MULTIVARIATE GAUSSIAN FEATURE ADAPTATION FOR DISTANT-TALKING SPEECH RECOGNITION | ||
| Authors: | Yue Pan; Carnegie Mellon University | ||
| Alex Waibel; Carnegie Mellon University | |||
| Abstract: | Multivariate Gaussian based speech compensation or mapping has been developed to reduce the mismatch between training and deployment conditions for robust speech recognition. The acoustic mapping procedure can be formulated as a feature space adaptation where input noisy signal is transformed by a multivariate Gaussian network. We propose a novel algorithm to update the network parameters based on minimizing the Kullback-Leibler distance between the core recognizer’s acoustic model and transformed features. It is designed to achieve optimal overall system performance rather than MMSE on a specific feature domain. An online stochastic gradient descent learning rule is derived. We evaluate the performance of the new algorithm using JRTk Broadcast news system on a distance-talking speech corpus and compare its performance with that of previous MMSE based approaches. The experiments show the KL based approach is more effective for a large vocabulary continuous speech recognition (LVCSR) system. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops