The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking
Open accessAbstract
Time delay neural network (TDNN) has been proven to be efficient for speaker verification. One of its successful variants, ECAPA-TDNN, achieved state-of-the-art performance at the cost of much higher computational complexity and slower inference speed. This makes it inadequate for scenarios with demanding inference rate and limited computational resources. We are thus interested in finding an architecture that can achieve the performance of ECAPA-TDNN and the efficiency of vanilla TDNN. In this paper, we propose an efficient network based on context-aware masking, namely CAM++, which uses densely connected time delay neural network (D-TDNN) as backbone and adopts a novel multi-granularity pooling to capture contextual information at different levels. Extensive experiments on two public benchmarks, VoxCeleb and CN-Celeb, demonstrate that the proposed architecture outperforms other mainstream speaker verification systems with lower computational cost and faster inference speed.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“The ASV model is the CAM++ model from Wang et al. (2023). It is chosen only for the reasons that it is different to the baseline ASV system described in Section 7.1 and that its use hence supports evaluation in a black-box setting.”
From ASVspoof 5: Design, collection and validation of resources for spoofing, deepfake, and adversarial attack detection using crowdsourced speech (2026) · cites this paper as Wang et al. (2023)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 4
- Y.-Q. Yu, S. Zheng, H. Suo, Y. Lei, and W.-J. Li, "Cam: Context- aware masking for robust speaker verification," in IEEE Interna- tional Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 6703-6707.
- B. Liu, Z. Chen, S. Wang, H. Wang, B. Han, and Y. Qian, "Df- resnet: Boosting speaker verification performance withdepth-first design," in Annual Conference of the International Speech Com- munication Association (INTERSPEECH), 2022, pp. 296-300.
- C. Tan, Q. Chen, W. Wang, Q. Zhang, S. Zheng, and Z. Ling, "Ponet: Pooling network for efficient token mixing in long se- quences," in The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022.
- M. Indiay, P. Safariy, and J. Hernando, "Self multi-head atten- tion for speaker recognition," in Annual Conference of the Inter- national Speech Communication Association (INTERSPEECH), 2019, pp. 4305-4309.
Cited by
Sorted by citations
Items 201–241 of 241
Enhancing Arabic Speaker Recognition with ECAPA-TDNN
Ayman, M., & Aloufi, F. A. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.13902
DS-CAM: Tibetan Speaker Verification with Depth-Wise Separable Module and Context-Aware Masking
Gan, Z., Wang, T., & Shan, J. (2026) · International Conference on Multi-scale Artificial Intelligence (MAI) · doi:10.1109/mai69289.2026.11543703
Hu, G., Wei, T., Luo, J.-Y., Huang, Z.-K., Zhao, X.-H., Chen, S., Wang, K., Liu, F., Peng, M., Xie, Q., et al. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116325
Popov, V., Gu, W., Sadekova, T., Aparin, G., & Yermekova, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.09962
Leveraging Large Language Models for Robust Speaker Verification
Zhang, X., Yuntao, S., & Sun, Y. W. (2026) · IEEE Access · doi:10.1109/access.2026.3703407
Dynamic Prosody Prediction in LLM-based TTS for Improving Speaker Similarity
Mou, Z., Chen, L., Hu, Y., Ling, Z.-H., Fang, X., & Gao (2026) · Interspeech (USB) · doi:10.21437/interspeech.2026-2312
Accent Conversion and Pronunciation Improvement
Nguyen, T. N. (2026) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5445/ir/1000194655
VocalRep: Structure-Aware Vocal Representations for Multimodal Generation
Shen, D., Weng, Z., Liu, T., Chen, G., Shi, R., Chen, J., Ding, C., Zhang, W.-Q., & Chen, Z. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.1785
DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement LearningPreprint
Huang, Y., Yao, W., Xiao, F., Chen, X., & Wen, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.01729
Reasoning LLM Improves Speaker Recognition in Long-form TV DramasPreprint
Li, Y., Xie, L., Huo, X., Qiu, J., Shao, J., Chen, P., Ge, J., Duan, K., & Tian, Q. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.02504
Huang, Y., Yao, W., Xiao, F., Chen, X., & Wen, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.01702
OU-MB: The OU Multimodal Biometric Database and Its Performance Evaluation
Xu, C., Li, X., Shehata, A., Aljazaerly, M. A. A., & Yagi, Y. (2026) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2026.3710514
Short-Utterance Authentication using Lexical Challenge and Speaker Verification
Snow, E., Bhattarakosol, P., & Luangsodsai, A. (2026) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse68839.2026.11597046
Improve Speaker Embedding Through Diffusion Generative Training
Tu, Y., Mak, M., Chien, J., & Zuo, L. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3714207
Rockfall Monitoring for Highways Based on Distributed Fiber Optics and Model Merging
Lyu, L., Lin, J., Guo-xu, C. H. E. N., Zhao, Q., Ni, Y.-Q., & WANG, Y.-W. (2026) · e-Journal of Nondestructive Testing · doi:10.58286/33948
Perceptual V-Cloak: Generating Trainable and Unintelligible Speech Dataset
Lin, Y., Ye, D., Deng, J., Wei, Z., & Liu, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3381-6_10
A Speaker Verification Method Based on Dual-Branch Multi-Scale Feature Aggregation
Wang, W. B., Zhang, W., & Cai, Z. (2026) · International Conference on Electrical, Control and Information Technology (ECITech) · doi:10.1109/ecitech69277.2026.11601924
Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker EncoderPreprint
Wang, H., Wang, H., Zhang, R., Li, Y., & Duan, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.11650
Self-citationNguyen, H. N., & Nguyen, H. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-2597-2_45
Speaker Recognition Model Based on Multi-Scale Feature Fusion and Dynamic Optimization
Zhang, T., Qu, D., Zeng, L., Wang, P., & Yang, C. (2026) · International Conference on Communication Engineering and Technology (ICCET) · doi:10.1109/iccet70051.2026.11659008
PersianVox: A Prosody-Aware Approach for Speech Dataset Generation from In-the-Wild DataPreprint
Zouashkiani, S., Khalesi, S., Roudi, S. S., Amini, S., & Ghaemmaghami, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.19324
Liao, H., Han, H., Han, X., Chen, D., Wang, Y., & Wu, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.24771
SceneTTS-Bench: A Benchmark for Scene-Level TTS in Drama DubbingPreprint
Geng, Y., Li, Y., Yang, J., Tianhan, J., Gao, Y., & Li, Y. W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.26255
Diagnosing Reference-Side Language and Dialect Leakage in Cross-Lingual Tibetan Voice Cloning
Dorjee, T., La, D., & Lengben, Z. (2026) · Applied Sciences · doi:10.3390/app16199466
From Reliable Text to Real Voices: Trust-Aware Progressive Adaptation for Low-Resource TTSPreprint
Lu, J., Geng, Y., Yang, J., Tianhan, J., An, B., Gao, Y., & Li, Y. (2026) · arXiv (Cornell University)
Unified Target-Speaker ASR with Text and Enrollment Speech CuesPreprint
Mei, Y., Yan, Y., Xu, D., Liang, J., & Long, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.33853
Liu, C., Fang, M., We, Z., Mao, S., Zhang, G., & Han, J. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3739182
Chen, J., Zhang, Y., & Vinton, M. S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.38658
Multimodal Co-Generation With Continuous Bitstream DiffusionPreprint
Batzolis, G., Kontos, G., Trentini, B., Chatterjee, P., Livne, M., Girolami, M., & Ambrogioni, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.14349
Jin, Z., Wang, X., Li, Z., Gan, C.-X., Qin, S., Mak, M., & Lee, K. A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.25892
Edit in Sync: Unified End-to-End Audio-Visual Editing for Human-Centric VideosPreprint
Yuan, Z., Cai, M., He, X., Yao, R., Fu, X., Ding, K., Zhang, M., Du, X., Lan, T., Xie, D., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.27947
General Speech Reconstruction for Voice Calls Using Smartphone's Built-in Accelerometer
Liu, G., Wang, L., Wang, X., Qiao, Q., Peng, C., Xiong, J., Dai, H., & Chen, G. (2026) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3795866.3844493
CVAE-ECA: A Stealthy Backdoor Attack Against Speech Classification via Emotion Conversion
Huang, Y., Yao, W., Chen, X., & Wen, W. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-6843-6_10
Zhang, X., Qi, X., Wang, J., & Xie, Y. (2026) · Applied Sciences · doi:10.3390/app162110529
MMR-constrained Voice Conversion for Deficient Speaker Dataset Augmentation
He, C., Peng, S., Lu, T., Zhao, K., & Zhang, L. (2026) · Circuits Systems and Signal Processing · doi:10.1007/s00034-026-03844-4
M3-TTS: Native Two-Stream Multi-Modal Diffusion Transformer for Zero-Shot Speech Synthesis
Wang, X., Qiang, C., Fu, R., Wen, Z., Guo, Y., Liu, X., Liu, Y., Liang, Y., Yin, K., Ma, T., et al. (2026) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/2026.findings-emnlp.240
Self-citationVoice Identification Based on the Use of Chirplet Transforms
Magzhan, A., Talgat, M., Othman, M., Sholpan, J., & Aigerim, M. (2026) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2026.0171082
FreqGuard: Leveraging Frequency-Domain Feature Priors for Universal Proactive Voice Defense
Yankai, 王. W., Chen, Z., Du, Y., Zheng, R., & Deng, J. (2026) · Interspeech (USB) · doi:10.21437/interspeech.2026-2069
Park, S., Kim, S., Park, S., Kim, D., Nguyen, T. A., Doan, T.-P., Jung, S., & Choi, D. (2026) · Interspeech (USB) · doi:10.21437/interspeech.2026-2944
Who is Talking to Me? Addressing Egocentric TTM with Speaker-aware Conversational Context
陳福坤, Zhong, X., & Cai, M. (2026) · Interspeech (USB) · doi:10.21437/interspeech.2026-2358
Zheng, Z., Ye, X., & Manoharan, S. (2026) · Research Square · doi:10.21203/rs.3.rs-11590288/v1
Metadata
- Authors
- Wang, H., Zheng, S., Chen, Y., Cheng, L., & Chen, Q.
- Venue
- INTERSPEECH 2023
- Publisher
- ISCA
- Published
- 2023-08-20
- Pages
- 5301-5305
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W4385823321
- Cited by
- 150
- References
- 0
- Citations by year
- 2026: 47 · 2025: 76 · 2024: 24 · 2023: 3
- FWCI
- 26.58
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Interspeech (USB) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- speaker verification, CAM, attention mechanism, deep learning architectures
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
