DeepDet: YAMNet with BottleNeck Attention Module (BAM) for TTS synthesis detection
Abstract Spoofed speeches are becoming a big threat to society due to advancements in artificial intelligence techniques. Therefore, there must be an automated spoofing detector that can be integrated into automatic speaker verification (ASV) systems. In this study, we recommend a novel and robust m...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-04-01
|
| Series: | EURASIP Journal on Audio, Speech, and Music Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13636-024-00335-9 |
| _version_ | 1827284168668610560 |
|---|---|
| author | Rabbia Mahum Aun Irtaza Ali Javed Haitham A. Mahmoud Haseeb Hassan |
| author_facet | Rabbia Mahum Aun Irtaza Ali Javed Haitham A. Mahmoud Haseeb Hassan |
| author_sort | Rabbia Mahum |
| collection | DOAJ |
| description | Abstract Spoofed speeches are becoming a big threat to society due to advancements in artificial intelligence techniques. Therefore, there must be an automated spoofing detector that can be integrated into automatic speaker verification (ASV) systems. In this study, we recommend a novel and robust model, named DeepDet, based on deep-layered architecture, to categorize speech into two classes: spoofed and bonafide. DeepDet is an improved model based on Yet Another Mobile Network (YAMNet) employing a customized MobileNet combined with a bottleneck attention module (BAM). First, we convert audio into mel-spectrograms that consist of time–frequency representations on mel-scale. Second, we trained our deep layered model using the extracted mel-spectrograms on a Logical Access (LA) set, including synthesized speeches and voice conversions of the ASVspoof-2019 dataset. In the end, we classified the audios, utilizing our trained binary classifier. More precisely, we utilized the power of layered architecture and guided attention that can discern the spoofed speech from bonafide samples. Our proposed improved model employs depth-wise linearly separate convolutions, which makes our model lighter weight than existing techniques. Furthermore, we implemented extensive experiments to assess the performance of the suggested model using the ASVspoof 2019 corpus. We attained an equal error rate (EER) of 0.042% on Logical Access (LA), whereas 0.43% on Physical Access (PA) attacks. Therefore, the performance of the proposed model is significant on the ASVspoof 2019 dataset and indicates the effectiveness of the DeepDet over existing spoofing detectors. Additionally, our proposed model is robust enough that can identify the unseen spoofed audios and classifies the several attacks accurately. |
| first_indexed | 2024-04-24T09:51:19Z |
| format | Article |
| id | doaj.art-a765588829b2424a80e3928d25e344e1 |
| institution | Directory Open Access Journal |
| issn | 1687-4722 |
| language | English |
| last_indexed | 2024-04-24T09:51:19Z |
| publishDate | 2024-04-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Audio, Speech, and Music Processing |
| spelling | doaj.art-a765588829b2424a80e3928d25e344e12024-04-14T11:23:52ZengSpringerOpenEURASIP Journal on Audio, Speech, and Music Processing1687-47222024-04-012024111610.1186/s13636-024-00335-9DeepDet: YAMNet with BottleNeck Attention Module (BAM) for TTS synthesis detectionRabbia Mahum0Aun Irtaza1Ali Javed2Haitham A. Mahmoud3Haseeb Hassan4Computer Science Department, UET TaxilaComputer Science Department, UET TaxilaSoftware Engineering Department, UET TaxilaIndustrial Engineering Department, College of Engineering, King Saud UniversityCollege of Big Data and Internet, Shenzhen Technology University (SZTU)Abstract Spoofed speeches are becoming a big threat to society due to advancements in artificial intelligence techniques. Therefore, there must be an automated spoofing detector that can be integrated into automatic speaker verification (ASV) systems. In this study, we recommend a novel and robust model, named DeepDet, based on deep-layered architecture, to categorize speech into two classes: spoofed and bonafide. DeepDet is an improved model based on Yet Another Mobile Network (YAMNet) employing a customized MobileNet combined with a bottleneck attention module (BAM). First, we convert audio into mel-spectrograms that consist of time–frequency representations on mel-scale. Second, we trained our deep layered model using the extracted mel-spectrograms on a Logical Access (LA) set, including synthesized speeches and voice conversions of the ASVspoof-2019 dataset. In the end, we classified the audios, utilizing our trained binary classifier. More precisely, we utilized the power of layered architecture and guided attention that can discern the spoofed speech from bonafide samples. Our proposed improved model employs depth-wise linearly separate convolutions, which makes our model lighter weight than existing techniques. Furthermore, we implemented extensive experiments to assess the performance of the suggested model using the ASVspoof 2019 corpus. We attained an equal error rate (EER) of 0.042% on Logical Access (LA), whereas 0.43% on Physical Access (PA) attacks. Therefore, the performance of the proposed model is significant on the ASVspoof 2019 dataset and indicates the effectiveness of the DeepDet over existing spoofing detectors. Additionally, our proposed model is robust enough that can identify the unseen spoofed audios and classifies the several attacks accurately.https://doi.org/10.1186/s13636-024-00335-9Deep learningSpoofing detectorFake speech detection |
| spellingShingle | Rabbia Mahum Aun Irtaza Ali Javed Haitham A. Mahmoud Haseeb Hassan DeepDet: YAMNet with BottleNeck Attention Module (BAM) for TTS synthesis detection EURASIP Journal on Audio, Speech, and Music Processing Deep learning Spoofing detector Fake speech detection |
| title | DeepDet: YAMNet with BottleNeck Attention Module (BAM) for TTS synthesis detection |
| title_full | DeepDet: YAMNet with BottleNeck Attention Module (BAM) for TTS synthesis detection |
| title_fullStr | DeepDet: YAMNet with BottleNeck Attention Module (BAM) for TTS synthesis detection |
| title_full_unstemmed | DeepDet: YAMNet with BottleNeck Attention Module (BAM) for TTS synthesis detection |
| title_short | DeepDet: YAMNet with BottleNeck Attention Module (BAM) for TTS synthesis detection |
| title_sort | deepdet yamnet with bottleneck attention module bam for tts synthesis detection |
| topic | Deep learning Spoofing detector Fake speech detection |
| url | https://doi.org/10.1186/s13636-024-00335-9 |
| work_keys_str_mv | AT rabbiamahum deepdetyamnetwithbottleneckattentionmodulebamforttssynthesisdetection AT aunirtaza deepdetyamnetwithbottleneckattentionmodulebamforttssynthesisdetection AT alijaved deepdetyamnetwithbottleneckattentionmodulebamforttssynthesisdetection AT haithamamahmoud deepdetyamnetwithbottleneckattentionmodulebamforttssynthesisdetection AT haseebhassan deepdetyamnetwithbottleneckattentionmodulebamforttssynthesisdetection |