JBT Journal
Advanced

Raqamli Transformatsiya va Sun’iy Intellekt

SO‘ZLOVCHILARNI AJRATISHDA ECAPA-TDNN ASOSIDAGI XUSUSIYATLAR VEKTORLARIDAN FOYDALANISH

Umidjon Xasanov Komiljon o‘g‘li1

1 Muhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti

Zenodo DOI: 10.5281/zenodo.22014404

Keywords

So‘zlovchilarni ajratish Spektral klasterlash ECAPA-TDNN so‘zlovchilarni ifodalovchi xususiyatlar vektori X-vektor

Abstract

So‘zlovchilarni ajratishda xususiyatlar vektorlarini shakllantirish eng muhim bosqichlardan biri hisoblanadi. Zamonaviy chuqur neyron tarmoqlar so‘zlovchining individual xususiyatlarini aniqlash va ularni ifodalashda yuqori aniqlikni ta’minlay oladi. Xususan, x-vector kabi mashhur xususiyatlar vektorlari hozirgi tizimlarda asosiy komponent sifatida qo‘llanib kelmoqda. So‘nggi yillarda TDNN arxitekturasi ustida turli takomillashtirishlar ishlab chiqildi. ECAPA-TDNN modeli esa o‘ziga xos kanal e’tibor mexanizmi va ko‘p qatlamli agregatsiya orqali so‘zlovchini tekshirish vazifalarida yuqori samaradorlikni ko‘rsatdi. Tadqiqot mazkur modelni diarizatsiya sohasiga tatbiq etish imkoniyatlarini namoyish etadi.

Views: 113 Published: 2025-12-28 Pages: 152-158 Volume: 3 Issue: 6

References

  1. S. Gao, M.-M. Cheng, K. Zhao, X. Zhang, M.-H. Yang, and P. H. S. Torr, “Res2Net: A new multi-scale backbone architecture,” IEEE TPAMI, pp. 652–662, 2019.
  2. J. Thienpondt, B. Desplanques, and K. Demuynck, “Cross-lingual speaker verification with domain-balanced hard prototype mining and language-dependent score normalization,” in Proc. Interspeech, 2020, pp. 756–760.
  3. B. Desplanques, J. Thienpondt, and K. Demuynck, “ECAPATDNN: Emphasized channel attention, propagation and aggregation in TDNN based speaker verification,” in Proc. Interspeech, 2020, pp. 3830–3834.
  4. Z. Gao, Y. Song, I. McLoughlin, P. Li, Y. Jiang, and L.-R. Dai, “Improving aggregation and loss function for better embedding learning in end-to-end speaker verification system,” in Proc. Interspeech, 2019, pp. 361–365.
  5. L. Wan, Q. Wang, A. Papir, and I. Lopez-Moreno, “Generalized end-to-end loss for speaker verification,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4879–4883, 2018.
  6. G. Sun, C. Zhang, and P. C. Woodland, “Speaker diarisation using 2d self-attentive combination of embeddings,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 5801–5805, 2019.
  7. E. Hoffer, T. Ben-Nun, I. Hubara, N. Giladi, T. Hoefler, and D. Soudry, “Augment your batch: better training with larger batches,” CoRR, vol. abs/1901.09335, 2019.
  8. T. J. Park, N. Kanda, D. Dimitriadis, K. J. Han, S. Watanabe, and S. Narayanan, “A review of speaker diarization: Recent advances with deep learning,” 2021, arXiv:2101.09624.
  9. Xasanov U.K., To‘rayev X.Sh., Tolibova N.D., “So‘zlovchilarni ajratish jarayonlarida nutq signallariga dastlabki ishlov berish”, 153-157b, 2025
  10. J. Hu, L. Shen, and G. Sun, “Squeeze-and-Excitation networks,” in IEEE/CVF CVPR, 2018, pp. 7132–7141.
  11. Shukurov K.E., Kaxxarov A.A., Xasanov U.K., “O‘qituvchisiz o‘qitish asosida so‘zlovchilarni ajratish”, “Raqamli transformatsiya: axborot texnologiyalari, sun’iy intellekt va iqtisodiyotda yangi davr”, 442-447b, 2025
  12. D. S. Park, W. Chan, Y. Zhang, C. Chiu, B. Zoph, E. D. Cubuk, and Q. V. Le, “Specaugment: A simple data augmentation method for automatic speech recognition,” in Proc. Interspeech, 2019, pp. 2613–2617.
  13. H. Zeinali, K. A. Lee, J. Alam, and L. Burget, “SdSV challenge 2020: Large-scale evaluation of short-duration speaker verification,” in Proc. Interspeech, 2020, pp. 731–735.
  14. G. Sell, D. Snyder, A. McCree, D. Garcia-Romero, J. Villalba, M. Maciejewski, V. Manohar, N. Dehak, D. Povey, S. Watanabe, and S. Khudanpur, “Diarization is hard: Some experiences and lessons learned for the JHU team in the inaugural DIHARD challenge,” in Proc. Interspeech, 2018, pp. 2808–2812.
  15. D. Garcia-Romero, G. Sell, and A. McCree, “Magneto: X-vector magnitude estimation network plus offset for improved speaker recognition,” in Proc. Odyssey, 2020, pp. 1–8.
  16. D. Snyder, D. Garcia-Romero, G. Sell, D. Povey, and S. Khudanpur, “X-vectors: Robust DNN embeddings for speaker recognition,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 5329–5333, 2018.
  17. N. Dawalatabad, S. Madikeri, C. C. Sekhar, and H. A. Murthy, “Novel architectures for unsupervised information bottleneck based speaker diarization of meetings,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 14–27, 2021.
  18. X. Anguera, S. Bozonnet, N. Evans, C. Fredouille, G. Friedland, and O. Vinyals, “Speaker diarization: A review of recent research,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 2, pp. 356–370, 2012.
  19. N. Ryant, K. Church, C. Cieri, A. Cristia, J. Du, S. Ganapathy, and M. Liberman, “The second DIHARD diarization challenge: Dataset, task, and baselines,” in Proc. Interspeech, 2019, pp. 978– 982.
  20. J. Deng, J. Guo, N. Xue, and S. Zafeiriou, “ArcFace: Additive angular margin loss for deep face recognition,” in IEEE/CVF CVPR, 2019, pp. 4685–4694.