Publication

International Journal Papers

  1. W. H. Kang, J. Alam, A. Fathan, “l-mix: a latent-level instance mixup regularization for robust self-supervised speaker representation learning,” IEEE Journal of Selected Topics in Signal Processing, vol. 16, no. 6, 2022. (SCI-E)
  2. H. Y. Kim, J. W. Yoon, S. J. Cheon, W. H. Kang, and N. S. Kim, “A multi-resolution approach to GAN-based speech enhancement,” Applied Sciences, vol. 11, no. 2, 2021. (SCI-E)
  3. H. Lee, W. H. Kang, S. J. Cheon, H. Kim, N. S. Kim, “Gated recurrent context: softmax-free attention for online encoder-decoder speech recognition,” IEEE Transactions on Audio, Speech, and Language Processing, vol 29, pp. 710-719, 2021. (SCI-E)
  4. W. H. Kang, S. H. Mun, M. H. Han, and N. S. Kim, “Disentangled speaker and nuisance attribute embedding for robust speaker verification,” IEEE Access, vol. 8, pp. 141838-141849, 2020. (SCI-E)
  5. W. H. Kang and N. S. Kim, “Adversarially learned total variability embedding for speaker recognition with random digit strings,” Sensors, vol. 19, no. 21, 2019. (SCI-E)
  6. W. H. Kang and N. S. Kim, “Unsupervised learning of total variability embedding for speaker verification with random digit strings,” Applied Sciences, vol. 9, no. 8, 2019. (SCI-E)

International Conference Papers

  1. G. Chochlakis, T. Iqbal, W. H. Kang, Z. Huang, “Modality-agnostic multimodal emotion recognition using a contrastive masked autoencoder,” in Proc. Interspeech, 2025.
  2. W. H. Kang, S. Vishnubhotla, R. Braun, Y. Virkar, R. Peri, and K. Han, “SWAN: subword alignment network for HMM-free word timing estimation in end-to-end automatic speech recognition,” in Proc. Interspeech, 2024.
  3. A. Fathan, J. Alam, and W. H. Kang, “Investigation of the quality of pseudo-labels for the self-supervised speaker verification task,” in Proc. ICASSP Workshops, 2023.
  4. J. Alam, W. H. Kang, and A. Fathan, “Hybrid neural network with cross- and self-module attention pooling for text-independent speaker verification,” in Proc. ICASSP, 2023.
  5. A. Fathan, J. Alam, and W. H. Kang, “On the impact of the quality of pseudo-labels on the self-supervised speaker verification task,” in Proc. NeurIPS workshop on Efficient Natural Language and Speech Processing, 2022.
  6. W. H. Kang, J. Alam, and A. Fathan, “Flow-ER: a flow-based embedding regularization strategy for robust speech representation learning,” in Proc. SLT, 2022.
  7. W. H. Kang, J. Alam, and A. Fathan, “An analytic study on clustering-based pseudo-labels for self-supervised deep speaker verification,” in Proc. SPECOM, 2022.
  8. J. Alam, W. H. Kang, and A. Fathan, “Neural embedding extractors for text-independent speaker verification,” in Proc. SPECOM, 2022.
  9. A. Fathan, J. Alam, and W. H. Kang, “Multiresolution decomposition analysis via wavelet transforms for audio deepfake detection,” in Proc. SPECOM, 2022.
  10. W. H. Kang, J. Alam, and A. Fathan, “MIM-DG: mutual information minimization-based domain generalization for speaker verification,” in Proc. Interspeech, 2022.
  11. W. H. Kang, J. Alam, and A. Fathan, “End-to-end framework for spoof-aware speaker verification,” in Proc. Interspeech, 2022.
  12. W. H. Kang, J. Alam, and A. Fathan, “Mixup regularization strategies for spoofing countermeasure systems,” in Proc. Interspeech, 2022.
  13. A. Fathan, J. Alam, and W. H. Kang, “Mel-spectrogram image-based end-to-end audio deepfake detection under channel-mismatched conditions,” in Proc. ICME, 2022.
  14. W. H. Kang and J. Alam, “Investigation on deep speaker embedding extraction methods for multi-genre speaker verification,” in Proc. Odyssey, 2022.
  15. W. H. Kang, J. Alam, and A. Fathan, “Investigation on mixup strategies for end-to-end voice spoof detection system,” in Proc. Odyssey, 2022.
  16. W. H. Kang, J. Alam, and A. Fathan, “Domain generalized speaker embedding learning via mutual information minimization,” in Proc. Odyssey, 2022.
  17. J. Alam, T. Stafylakis, A. Silnova, O. Pichot, P. Matejka, A. Fathan, and W. H. Kang, “Development of ABC systems for the 2021 edition of NIST speaker recognition evaluation,” in Proc. Odyssey, 2022.
  18. J. Alam, A. Fathan, and W. H. Kang, “Hybrid neural network-based deep embedding extractors for text-independent speaker verification,” in Proc. Odyssey, 2022.
  19. W. H. Kang, J. Alam, and A. Fathan, “Deep learning-based end-to-end spoken language identification system for domain-mismatched scenario,” in Proc. LREC, 2022.
  20. W. H. Kang, J. Alam, and A. Fathan, “Robust self-supervised speaker representation learning via instance mix regularization,” in Proc. ICASSP, 2022.
  21. W. H. Kang, J. Alam, and A. Fathan, “Investigation on instance mixup regularization strategies for self-supervised speaker representation learning,” in Proc. AAAI workshop on Self-supervised Learning for Audio and Speech Processing, 2022.
  22. W. H. Kang, J. Alam, and A. Fathan, “Hybrid network with multi-level global-local statistics pooling for robust text-independent speaker recognition,” in Proc. ASRU, 2021.
  23. W. H. Kang, J. Alam, and A. Fathan, “Investigation on activation functions for robust end-to-end spoofing attack detection system,” in Proc. Interspeech satellite workshop on ASVSpoof2021, 2021.
  24. W. H. Kang, J. Alam, and A. Fathan, “CRIM’s system description for the ASVSpoof2021 challenge,” in Proc. Interspeech satellite workshop on ASVSpoof2021, 2021.
  25. A. Fathan, J. Alam, and W. H. Kang, “An ensemble approach for the diagnosis of COVID-19 from speech and cough sounds,” in Proc. SPECOM, 2021.
  26. J. Alam, A. Fathan, and W. H. Kang, “End-to-end voice spoofing detection employing time delay neural networks and higher order statistics,” in Proc. SPECOM, 2021.
  27. J. Alam, A. Fathan, and W. H. Kang, “Text-dependent speaker verification employing CNN-LSTM-TDNN hybrid networks,” in Proc. SPECOM, 2021.
  28. W. I. Cho, S. J. Cheon, W. H. Kang, J. W. Kim, and N. S. Kim, “Giving space to your message: assistive word segmentation for the electronic typing of digital minorities,” in Proc. Designing Interactive Systems Conference, 2021, pp. 1739-1747.
  29. W. H. Kang and N. S. Kim, “Team02 text-independent speaker verification system for SdSV Challenge 2021,” in Proc. Interspeech, 2021.
  30. H. J. Kim, H. S. Lee, W. H. Kang, J. Y. Lee, and N. S. Kim, “SoftFlow: probabilistic framework for normalizing flow on manifolds,” in Proc. NeurIPS, 2020.
  31. S. H. Mun, W. H. Kang, M. H. Han, and N. S. Kim, “Robust text-dependent speaker verification via character-level information preservation for the SdSV Challenge 2020,” in Proc. Interspeech, 2020.
  32. H. J. Kim, H. Lee, W. H. Kang, S. J. Cheon, B. J. Choi, and N. S. Kim, “WaveNODE: a continuous normalizing flow for speech synthesis,” in Proc. ICML workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, 2020.
  33. H. J. Kim, H. S. Lee, W. H. Kang, H. Y. Kim, and N. S. Kim, “Robust front-end for multi-channel flow-based density estimation,” in Proc. IJCAI-PRICAI, 2020.
  34. M. H. Han, W. H. Kang, S. H. Mun, and N. S. Kim, “Information preservation pooling for speaker embedding,” in Proc. Odyssey, 2020, pp. 60-66.
  35. W. I. Cho, J. Cho, W. H. Kang, and N. S. Kim, “Text matters but speech influences: A computational analysis of syntactic ambiguity resolution,” in Proc. CogSci, 2020.
  36. H. Lee, H. Y. Kim, W. H. Kang, J. Kim, and N. S. Kim, “End-to-end multi-channel speech enhancement using inter-channel time-restricted attention on raw waveform,” in Proc. Interspeech, 2019.
  37. K. H. Lee, W. H. Kang, H. Lee, and N. S. Kim, “Stochastic DNN-HMM training for robust ASR,” in Proc. APSIPA, 2018.
  38. W. I. Cho, W. H. Kang, and N. S. Kim, “Hashcount at semeval-2018 task 3: concatenative featurization of tweet and hashtags for irony detection,” in Proc. SEMEVAL, 2018.
  39. W. H. Kang, W. I. Cho, S. Y. Jang, H. Lee, and N. S. Kim, “I-vector extraction using speaker relevancy for short duration speaker recognition,” in Proc. IT Convergence and Security, 2017.
  40. W. I. Cho, W. H. Kang, H. Lee, and N. S. Kim, “Detecting oxymoron in a single statement,” in Proc. O-COCOSDA, 2017.
  41. K. H. Lee, W. H. Kang, T. G. Kang, and N. S. Kim, “Integrated DNN-based model adaptation technique for noise-robust speech recognition,” in Proc. ICASSP, 2017.
  42. T. G. Kang, K. H. Lee, W. H. Kang, S. H. Bae, and N. S. Kim, “DNN-based voice activity detection with local feature shift technique,” in Proc. APSIPA, 2016.
  43. K. H. Lee, T. G. Kang, W. H. Kang, and N. S. Kim, “DNN-based feature enhancement using joint training framework for robust multichannel speech recognition,” in Proc. Interspeech, 2016.
  44. K. H. Lee, S. J. Kang, W. H. Kang, and N. S. Kim, “Two-stage noise aware training using asymmetric deep denoising autoencoder,” in Proc. ICASSP, 2016.

Korean Domestic Journal Papers

  1. 강우현 (W. H. Kang), 조원익, 강태균, 김남수, “i-벡터 기반 오픈세트 언어 인식을 위한 다중 판별 DNN,” 한국통신학회 논문지, vol. 41, no. 8, 2016.

Korean Domestic Conference Papers (1st author)

  1. 강우현 (W. H. Kang), 문성환, 한민현, 김남수, “화자 인식에서의 i-벡터 불확실성을 고려하기 위한 DNN 기반 특징 변환 기법,” 한국통신학회 하계종합학술발표회, 2018.
  2. 강우현 (W. H. Kang), 이강현, 강태균, 조원익, 김남수, “VAE를 이용한 화자 인식을 위한 음성 특징 추출,” 한국통신학회 동계종합학술발표회, 2017.
  3. 강우현 (W. H. Kang), 조원익, 강태균, 김남수, “i-벡터 기반 오픈세트 언어 인식을 위한 다중 판별 DNN,” 한국통신학회 논문지, vol. 41, no. 8, 2016.
  4. 강우현 (W. H. Kang), 조원익, 강태균, 김남수, 양성준, “DNN을 이용한 i-벡터 기반 오픈 세트 언어 인식,” 한국통신학회 동계종합학술발표회, 2016.
  5. 강우현 (W. H. Kang), 이강현, 강태균, 강신재, 김남수, 신강준, “피치와 MFCC로 학습한 i-벡터 틍징을 이용하는 화자 연령 회귀,” 한국통신학회 하계학술대회, 2015.
  6. 강우현 (W. H. Kang), 이강현, 강태균, 김남수, “i-벡터 특징을 이용하는 NN 기반의 화자 연령 분류,” 한국통신학회 추계종합학술대회, 2015.