Speaker independent continuous speech recognition

Speaker independent continuous speech recognition

This report presents a detail study on psychoacoustic modeling for feature extraction for robust continuous speech recognition. In an automatic speech recognition (ASR) system, feature extraction is critical to determining the recognizer’s performance. The most popular feature vectors for ASR are Me...

Full description

Saved in:
Bibliographic Details
Main Author: Soon, Ing Yann.
Other Authors: School of Electrical and Electronic Engineering
Format: Research Report
Language:English
Published: 2012
Subjects:
DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Online Access:http://hdl.handle.net/10356/47728
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-47728
record_format dspace
spelling sg-ntu-dr.10356-477282023-03-04T03:24:16Z Speaker independent continuous speech recognition Soon, Ing Yann. School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing This report presents a detail study on psychoacoustic modeling for feature extraction for robust continuous speech recognition. In an automatic speech recognition (ASR) system, feature extraction is critical to determining the recognizer’s performance. The most popular feature vectors for ASR are Mel Frequency Cepstral Coefficients (MFCC). However, it is also well known that its performance drops dramatically under noisy condition. One of the objectives of this research is to improve on the robustness of a continuous speech recognizer. RGM 8/06 2012-01-26T02:22:28Z 2012-01-26T02:22:28Z 2008 2008 Research Report http://hdl.handle.net/10356/47728 en 80 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
spellingShingle DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Soon, Ing Yann.
Speaker independent continuous speech recognition
description This report presents a detail study on psychoacoustic modeling for feature extraction for robust continuous speech recognition. In an automatic speech recognition (ASR) system, feature extraction is critical to determining the recognizer’s performance. The most popular feature vectors for ASR are Mel Frequency Cepstral Coefficients (MFCC). However, it is also well known that its performance drops dramatically under noisy condition. One of the objectives of this research is to improve on the robustness of a continuous speech recognizer.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Soon, Ing Yann.
format Research Report
author Soon, Ing Yann.
author_sort Soon, Ing Yann.
title Speaker independent continuous speech recognition
title_short Speaker independent continuous speech recognition
title_full Speaker independent continuous speech recognition
title_fullStr Speaker independent continuous speech recognition
title_full_unstemmed Speaker independent continuous speech recognition
title_sort speaker independent continuous speech recognition
publishDate 2012
url http://hdl.handle.net/10356/47728
_version_ 1759857380722475008

Similar Items