NSQM: A non-intrusive assessment of speech quality using normalized energies of the neurogram
This study proposes a new non-intrusive measure of speech quality, the neurogram speech quality measure (NSQM), based on the responses of a biologically-inspired computational model of the auditory system for listeners with normal hearing. The model simulates the responses of an auditory-nerve fiber...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2019
|
| Subjects: |
| _version_ | 1796961959734673408 |
|---|---|
| author | Jassim, Wissam A. Zilany, Muhammad Shamsul Arefeen |
| author_facet | Jassim, Wissam A. Zilany, Muhammad Shamsul Arefeen |
| author_sort | Jassim, Wissam A. |
| collection | UM |
| description | This study proposes a new non-intrusive measure of speech quality, the neurogram speech quality measure (NSQM), based on the responses of a biologically-inspired computational model of the auditory system for listeners with normal hearing. The model simulates the responses of an auditory-nerve fiber with a characteristic frequency to a speech signal, and the population response of the model is represented by a neurogram (2D time-frequency representation). The responses of each characteristic frequency in the neurogram were decomposed into sub-bands using 1D discrete Wavelet transform. The normalized energy corresponding to each sub-band was used as an input to a support vector regression model to predict the quality score of the processed speech. The performance of the proposed non-intrusive measure was compared to the results from a range of intrusive and non-intrusive measures using three standard databases: the EXP1 and EXP3 of supplement 23 to the P series (P.Supp23) of ITU-T Recommendations and the NOIZEUS databases. The proposed NSQM achieved an overall better result over most of the existing metrics for the effects of compression codecs, additive and channel noises. © 2019 |
| first_indexed | 2024-03-06T06:01:54Z |
| format | Article |
| id | um.eprints-24134 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T06:01:54Z |
| publishDate | 2019 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | um.eprints-241342020-04-03T05:17:11Z http://eprints.um.edu.my/24134/ NSQM: A non-intrusive assessment of speech quality using normalized energies of the neurogram Jassim, Wissam A. Zilany, Muhammad Shamsul Arefeen R Medicine TK Electrical engineering. Electronics Nuclear engineering This study proposes a new non-intrusive measure of speech quality, the neurogram speech quality measure (NSQM), based on the responses of a biologically-inspired computational model of the auditory system for listeners with normal hearing. The model simulates the responses of an auditory-nerve fiber with a characteristic frequency to a speech signal, and the population response of the model is represented by a neurogram (2D time-frequency representation). The responses of each characteristic frequency in the neurogram were decomposed into sub-bands using 1D discrete Wavelet transform. The normalized energy corresponding to each sub-band was used as an input to a support vector regression model to predict the quality score of the processed speech. The performance of the proposed non-intrusive measure was compared to the results from a range of intrusive and non-intrusive measures using three standard databases: the EXP1 and EXP3 of supplement 23 to the P series (P.Supp23) of ITU-T Recommendations and the NOIZEUS databases. The proposed NSQM achieved an overall better result over most of the existing metrics for the effects of compression codecs, additive and channel noises. © 2019 Elsevier 2019 Article PeerReviewed Jassim, Wissam A. and Zilany, Muhammad Shamsul Arefeen (2019) NSQM: A non-intrusive assessment of speech quality using normalized energies of the neurogram. Computer Speech & Language, 58. pp. 260-279. ISSN 0885-2308, DOI https://doi.org/10.1016/j.csl.2019.04.005 <https://doi.org/10.1016/j.csl.2019.04.005>. https://doi.org/10.1016/j.csl.2019.04.005 doi:10.1016/j.csl.2019.04.005 |
| spellingShingle | R Medicine TK Electrical engineering. Electronics Nuclear engineering Jassim, Wissam A. Zilany, Muhammad Shamsul Arefeen NSQM: A non-intrusive assessment of speech quality using normalized energies of the neurogram |
| title | NSQM: A non-intrusive assessment of speech quality using normalized energies of the neurogram |
| title_full | NSQM: A non-intrusive assessment of speech quality using normalized energies of the neurogram |
| title_fullStr | NSQM: A non-intrusive assessment of speech quality using normalized energies of the neurogram |
| title_full_unstemmed | NSQM: A non-intrusive assessment of speech quality using normalized energies of the neurogram |
| title_short | NSQM: A non-intrusive assessment of speech quality using normalized energies of the neurogram |
| title_sort | nsqm a non intrusive assessment of speech quality using normalized energies of the neurogram |
| topic | R Medicine TK Electrical engineering. Electronics Nuclear engineering |
| work_keys_str_mv | AT jassimwissama nsqmanonintrusiveassessmentofspeechqualityusingnormalizedenergiesoftheneurogram AT zilanymuhammadshamsularefeen nsqmanonintrusiveassessmentofspeechqualityusingnormalizedenergiesoftheneurogram |