Neural Network Front-ends Based Speech Recognition in Reverberant Environments
Zhen Zhang, Peng Li
Available Online August 2016.
- https://doi.org/10.2991/cset-16.2016.50How to use a DOI?
- REVERB Challenge, deep neural networks, Der-everberation, speech recognition
- This paper presents an investigation of reverberant speech recognition using frond-ends based methods. A 2-channel dereverberation method is adopted to achieve robust derever-beration under different reverberant conditions. Also a 2-channel spectral enhancement method is used where the gain of each frequency bin is controlled by acoustic scene, which is detected based on the analysis of full-band coherent property. Deep Neural Network (DNN) is also presented as a feature extractor. The DNN based front-end allows a very flexible integration of meta-information. Bottle neck features is extracted in place of MFCC features used in HMM-GMM system. We evaluated our methods on the data provided by REVERB challenge. On simulated data, the DNN front-end yields more than 33% relative reduction in Word Error Rate (WER).
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Zhen Zhang AU - Peng Li PY - 2016/08 DA - 2016/08 TI - Neural Network Front-ends Based Speech Recognition in Reverberant Environments BT - 2016 International Conference on Computer Science and Electronic Technology PB - Atlantis Press SN - 2352-538X UR - https://doi.org/10.2991/cset-16.2016.50 DO - https://doi.org/10.2991/cset-16.2016.50 ID - Zhang2016/08 ER -