An investigation of spoofing speech detection under additive noise and reverberant conditions
Spoofing detection for automatic speaker verification (ASV), which is to discriminate between live and artificial speech, has received increasing attentions recently. However, the previous studies have been done on the clean data without significant noise. It is still not clear whether the spoofing...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/89625 http://hdl.handle.net/10220/50288 |
| _version_ | 1826125335611047936 |
|---|---|
| author | Tian, Xiaohai Wu, Zhizheng Xiao, Xiong Chng, Eng Siong Li, Haizhou |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Tian, Xiaohai Wu, Zhizheng Xiao, Xiong Chng, Eng Siong Li, Haizhou |
| author_sort | Tian, Xiaohai |
| collection | NTU |
| description | Spoofing detection for automatic speaker verification (ASV), which is to discriminate between live and artificial speech, has received increasing attentions recently. However, the previous studies have been done on the clean data without significant noise. It is still not clear whether the spoofing detectors trained on clean speech can generalise well under noisy conditions. In this work, we perform an investigation of spoofing detection under additive noise and reverberant conditions. In particular, we consider five difference additive noises at three different signalto-noise ratios (SNR), and a reverberation noise with different reverberation time (RT). Our experimental results reveal that additive noises degrade the spoofing detectors trained on clean speech significantly. However, the reverberation does not hurt the performance too much. |
| first_indexed | 2024-10-01T06:34:57Z |
| format | Conference Paper |
| id | ntu-10356/89625 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:34:57Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/896252020-09-26T22:15:54Z An investigation of spoofing speech detection under additive noise and reverberant conditions Tian, Xiaohai Wu, Zhizheng Xiao, Xiong Chng, Eng Siong Li, Haizhou School of Computer Science and Engineering Interspeech 2016 Temasek Laboratories Spoofing Detection Noisy Database Engineering::Computer science and engineering Spoofing detection for automatic speaker verification (ASV), which is to discriminate between live and artificial speech, has received increasing attentions recently. However, the previous studies have been done on the clean data without significant noise. It is still not clear whether the spoofing detectors trained on clean speech can generalise well under noisy conditions. In this work, we perform an investigation of spoofing detection under additive noise and reverberant conditions. In particular, we consider five difference additive noises at three different signalto-noise ratios (SNR), and a reverberation noise with different reverberation time (RT). Our experimental results reveal that additive noises degrade the spoofing detectors trained on clean speech significantly. However, the reverberation does not hurt the performance too much. Published version 2019-10-30T07:15:07Z 2019-12-06T17:29:48Z 2019-10-30T07:15:07Z 2019-12-06T17:29:48Z 2016-09-01 2016 Conference Paper Tian, X., Wu, Z., Xiao, X., Chng, E. S., & Li, H. (2016). An investigation of spoofing speech detection under additive noise and reverberant conditions. Interspeech 2016. doi:10.21437/Interspeech.2016-743 https://hdl.handle.net/10356/89625 http://hdl.handle.net/10220/50288 10.21437/Interspeech.2016-743 200450 en © 2016 International Speech Communication Association (ISCA). All rights reserved. This paper was published in Interspeech 2016 and is made available with permission of International Speech Communication Association (ISCA). 5 p. application/pdf |
| spellingShingle | Spoofing Detection Noisy Database Engineering::Computer science and engineering Tian, Xiaohai Wu, Zhizheng Xiao, Xiong Chng, Eng Siong Li, Haizhou An investigation of spoofing speech detection under additive noise and reverberant conditions |
| title | An investigation of spoofing speech detection under additive noise and reverberant conditions |
| title_full | An investigation of spoofing speech detection under additive noise and reverberant conditions |
| title_fullStr | An investigation of spoofing speech detection under additive noise and reverberant conditions |
| title_full_unstemmed | An investigation of spoofing speech detection under additive noise and reverberant conditions |
| title_short | An investigation of spoofing speech detection under additive noise and reverberant conditions |
| title_sort | investigation of spoofing speech detection under additive noise and reverberant conditions |
| topic | Spoofing Detection Noisy Database Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/89625 http://hdl.handle.net/10220/50288 |
| work_keys_str_mv | AT tianxiaohai aninvestigationofspoofingspeechdetectionunderadditivenoiseandreverberantconditions AT wuzhizheng aninvestigationofspoofingspeechdetectionunderadditivenoiseandreverberantconditions AT xiaoxiong aninvestigationofspoofingspeechdetectionunderadditivenoiseandreverberantconditions AT chngengsiong aninvestigationofspoofingspeechdetectionunderadditivenoiseandreverberantconditions AT lihaizhou aninvestigationofspoofingspeechdetectionunderadditivenoiseandreverberantconditions AT tianxiaohai investigationofspoofingspeechdetectionunderadditivenoiseandreverberantconditions AT wuzhizheng investigationofspoofingspeechdetectionunderadditivenoiseandreverberantconditions AT xiaoxiong investigationofspoofingspeechdetectionunderadditivenoiseandreverberantconditions AT chngengsiong investigationofspoofingspeechdetectionunderadditivenoiseandreverberantconditions AT lihaizhou investigationofspoofingspeechdetectionunderadditivenoiseandreverberantconditions |