NDLI: Parallelized feature extraction and acoustic model training

Content Provider	IEEE Xplore Digital Library
Author	Haofeng Kou Weijia Shang
Copyright Year	2014
Description	Author affiliation: Santa Clara Univ., Santa Clara, CA, USA (Haofeng Kou; Weijia Shang)
Abstract	In this paper, we present our research on the parallelized speech recognition including both Mel-Frequency Cepstral Coefficient (MFCC) feature extraction [1] and Viterbi training for Hidden Markov Model (HMM) based acoustic model [2] on the Graphics Processing Units (GPU). Robust and accurate speech recognition systems can only be realized with adequately trained acoustic models derived from the effectively parsed features. For common languages, state-of-the-art systems are extracted and trained on many thousands of hours of speech data and even with large clusters of machines the entire extracting and training process can take weeks. To overcome this development bottleneck, we not only demonstrate that feature extraction and acoustic model training are suitable for GPUs, but also propose the optimized parallel implementation using highly parallel GPUs by combining the MFCC feature extraction along with Viterbi training for HMM acoustic model, illustrate its application concurrency characteristics, data working set sizes, and describe the optimizations required for effective throughput on GPU processors. We demonstrate that feature extraction and acoustic model training are well suited for GPUs. Using one GTX580 our approach is shown to be overall approximately 95x faster than a sequential CPU implementation at the same accuracy level, enabling feature extraction and acoustic model training to be performed at realtime.
Starting Page	503
Ending Page	508
File Size	1166209
Page Count	6
File Format	PDF
ISBN	9781479946129
ISSN	21653577
DOI	10.1109/ICDSP.2014.6900717
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2014-08-20
Publisher Place	China
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Hidden Markov models Training Graphics processing units Feature extraction Instruction sets Mel frequency cepstral coefficient CUDA Continuous Speech Recognition MFCC Feature Extraction Acoustic Model Training HMM GPU
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

Optimized MFCC feature extraction on GPU

HMM based isolated Kannada digit recognition system using MFCC

Devnagari Phoneme Recognition System

Transcribing deaf and hard of hearing speech using Hidden markov model

Impact of gender and emotion type in dialogue emotion recognition

Continuous Hindi speech recognition using Gaussian mixture HMM

Comparison of DTW and HMM for isolated word recognition

A novel approach for speech feature extraction by Cubic-Log compression in MFCC

A MFCC based Hindi speech recognition technique using HTK Toolkit

Parallelized feature extraction and acoustic model training

Similar Documents

Optimized MFCC feature extraction on GPU

HMM based isolated Kannada digit recognition system using MFCC

Devnagari Phoneme Recognition System

Transcribing deaf and hard of hearing speech using Hidden markov model

Impact of gender and emotion type in dialogue emotion recognition

Continuous Hindi speech recognition using Gaussian mixture HMM

Comparison of DTW and HMM for isolated word recognition

A novel approach for speech feature extraction by Cubic-Log compression in MFCC

A MFCC based Hindi speech recognition technique using HTK Toolkit

Parallelized feature extraction and acoustic model training