NDLI: Discriminative piecewise linear transformation based on deep learning for noise robust automatic speech recognition

Content Provider	IEEE Xplore Digital Library
Author	Kashiwagi, Y. Saito, D. Minematsu, N. Hirose, K.
Copyright Year	2013
Description	Author affiliation: Interfaculty Initiative in Inf. Studies, Univ. of Tokyo, Tokyo, Japan (Saito, D.) \|\| Grad. Sch. of Eng., Univ. of Tokyo, Tokyo, Japan (Kashiwagi, Y.; Minematsu, N.) \|\| Grad. Sch. of Inf. Sci. & Technol., Univ. of Tokyo, Tokyo, Japan (Hirose, K.)
Abstract	In this paper, we propose the use of deep neural networks to expand conventional methods of statistical feature enhancement based on piecewise linear transformation. Stereo-based piecewise linear compensation for environments (SPLICE), which is a powerful statistical approach for feature enhancement, models the probabilistic distribution of input noisy features as a mixture of Gaussians. However, soft assignment of an input vector to divided regions is sometimes done inadequately and the vector comes to go through inadequate conversion. Especially when conversion has to be linear, the conversion performance will be easily degraded. Feature enhancement using neural networks is another powerful approach which can directly model a non-linear relationship between noisy and clean feature spaces. In this case, however, it tends to suffer from over-fitting problems. In this paper, we attempt to mitigate this problem by reducing the number of model parameters to estimate. Our neural network is trained whose output layer is associated with the states in the clean feature space, not in the noisy feature space. This strategy makes the size of the output layer independent of the kind of a given noisy environment. Firstly, we characterize the distribution of clean features as a Gaussian mixture model and then, by using deep neural networks, estimate discriminatively the state in the clean space that an input noisy feature corresponds to. Experimental evaluations using the Aurora 2 dataset demonstrate that our proposed method has the best performance compared to conventional methods.
Starting Page	350
Ending Page	355
File Size	148694
Page Count	6
File Format	PDF
ISBN	9781479927562
DOI	10.1109/ASRU.2013.6707755
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2013-12-08
Publisher Place	Czech Republic
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Noise measurement Signal to noise ratio Speech Neural networks Training Vectors Deep learning Automatic speech recognition Noise robustness feature enhancement
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Discriminative Piecewise Linear Transformation Based on Deep Neural Networks for Noise Robust Automatic Speech Recognition

Audio-visual feature integration based on piecewise linear transformation for noise robust automatic speech recognition

Noisy training for deep neural networks

Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks

Feature enhancement by speaker-normalized splice for robust speech recognition

Incorporating mask modelling for noise-robust automatic speech recognition

Cepstral noise subtraction for robust automatic speech recognition

Speech Separation based on signal-noise-dependent deep neural networks for robust speech recognition

Feature enhancement based on generative-discriminative hybrid approach with gmms and DNNS for noise robust speech recognition

Discriminative piecewise linear transformation based on deep learning for noise robust automatic speech recognition

Similar Documents

Discriminative Piecewise Linear Transformation Based on Deep Neural Networks for Noise Robust Automatic Speech Recognition

Audio-visual feature integration based on piecewise linear transformation for noise robust automatic speech recognition

Noisy training for deep neural networks

Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks

Feature enhancement by speaker-normalized splice for robust speech recognition

Incorporating mask modelling for noise-robust automatic speech recognition

Cepstral noise subtraction for robust automatic speech recognition

Speech Separation based on signal-noise-dependent deep neural networks for robust speech recognition

Feature enhancement based on generative-discriminative hybrid approach with gmms and DNNS for noise robust speech recognition

Discriminative piecewise linear transformation based on deep learning for noise robust automatic speech recognition