Psychoacoustic model for robust speech recognition
This thesis presents a detailed study on psychoacoustic modeling for feature extraction for robust 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 Fr...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2010
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/41749 |
| _version_ | 1826115543710564352 |
|---|---|
| author | Luo, Xue Wen |
| author2 | Soon Ing Yann |
| author_facet | Soon Ing Yann Luo, Xue Wen |
| author_sort | Luo, Xue Wen |
| collection | NTU |
| description | This thesis presents a detailed study on psychoacoustic modeling for feature extraction for robust 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 thesis is to improve the robustness of a recognizer. Compared to an ASR system, human is good at tolerating background noise, hence psychoacoustic modeling of human hearing system is investigated and integrated into speech features extraction process of a speech recognizer to increase the robustness of it. |
| first_indexed | 2024-10-01T03:56:54Z |
| format | Thesis |
| id | ntu-10356/41749 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:56:54Z |
| publishDate | 2010 |
| record_format | dspace |
| spelling | ntu-10356/417492023-07-04T17:05:46Z Psychoacoustic model for robust speech recognition Luo, Xue Wen Soon Ing Yann School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing This thesis presents a detailed study on psychoacoustic modeling for feature extraction for robust 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 thesis is to improve the robustness of a recognizer. Compared to an ASR system, human is good at tolerating background noise, hence psychoacoustic modeling of human hearing system is investigated and integrated into speech features extraction process of a speech recognizer to increase the robustness of it. MASTER OF ENGINEERING (EEE) 2010-08-06T07:21:23Z 2010-08-06T07:21:23Z 2008 2008 Thesis Luo, X. W. (2008). Psychoacoustic model for robust speech recognition. Master’s thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/41749 10.32657/10356/41749 en 108 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Luo, Xue Wen Psychoacoustic model for robust speech recognition |
| title | Psychoacoustic model for robust speech recognition |
| title_full | Psychoacoustic model for robust speech recognition |
| title_fullStr | Psychoacoustic model for robust speech recognition |
| title_full_unstemmed | Psychoacoustic model for robust speech recognition |
| title_short | Psychoacoustic model for robust speech recognition |
| title_sort | psychoacoustic model for robust speech recognition |
| topic | DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing |
| url | https://hdl.handle.net/10356/41749 |
| work_keys_str_mv | AT luoxuewen psychoacousticmodelforrobustspeechrecognition |