Papers

On the Disentanglement and Robustness of Self-Supervised Speech Representations

International Conference
2021~
작성자
dsp
작성일
2024-01-22 16:25
조회
155
Authors : Yanjue Song, Doyeon Kim, Nilesh Madhu, Hong-Goo Kang

Year : 2024

Publisher / Conference : International Conference on Electronics, Information, and Communication (ICEIC) (*awarded Best Paper)

Research area : Speech Signal Processing

Presentation/Publication date : 2024.01.30

Presentation : Oral

This paper conducts an analysis of latent embeddings generated by a range of pre-trained, self-supervised learning (SSL) models. Departing from conventional practices that predominantly focus on examining these embeddings within the realm of speech recognition tasks, our study investigates the characteristics associated with speakers and their behavior under the influence of input distortions. We establish a controlled setting with varying background noise levels and different room impulse response conditions to assess the robustness of these embeddings. We measure speaker-related information by utilizing repetitive sentences spoken by multiple speakers. The results demonstrate that the robustness of pre-trained SSL models is influenced by the type and severity of distortion, whereas the inclusion of speaker information is determined by the specific pre-training approach employed. This distinct perspective offers valuable insights into the versatility and limitations of SSL models.
전체 355
38 International Conference Hyewon Han, Naveen Kumar "A cross-talk robust multichannel VAD model for multiparty agent interactions trained using synthetic re-recordings" in Hands-free Speech Communication and Microphone Arrays (HSCMA, Satellite workshop in ICASSP), 2024
37 International Conference Yanjue Song, Doyeon Kim, Nilesh Madhu, Hong-Goo Kang "On the Disentanglement and Robustness of Self-Supervised Speech Representations" in International Conference on Electronics, Information, and Communication (ICEIC) (*awarded Best Paper), 2024
36 International Conference Yeona Hong, Miseul Kim, Woo-Jin Chung, Hong-Goo Kang "Contextual Learning for Missing Speech Automatic Speech Recognition" in International Conference on Electronics, Information, and Communication (ICEIC), 2024
35 International Conference Juhwan Yoon, Seyun Um, Woo-Jin Chung, Hong-Goo Kang "SC-ERM: Speaker-Centric Learning for Speech Emotion Recognition" in International Conference on Electronics, Information, and Communication (ICEIC), 2024
34 International Conference Hejung Yang, Hong-Goo Kang "On Fine-Tuning Pre-Trained Speech Models With EMA-Target Self-Supervised Loss" in ICASSP, 2024
33 International Journal Zainab Alhakeem, Se-In Jang, Hong-Goo Kang "Disentangled Representations in Local-Global Contexts for Arabic Dialect Identification" in Transactions on Audio, Speech, and Language Processing, 2024
32 International Conference Hong-Goo Kang, W. Bastiaan Kleijn, Jan Skoglund, Michael Chinen "Convolutional Transformer for Neural Speech Coding" in Audio Engineering Society Convention, 2023
31 International Conference Hong-Goo Kang, Jan Skoglund, W. Bastiaan Kleijn, Andrew Storus, Hengchin Yeh "A High-Rate Extension to Soundstream" in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2023
30 International Conference Zhenyu Piao, Hyungseob Lim, Miseul Kim, Hong-goo Kang "PDF-NET: Pitch-adaptive Dynamic Filter Network for Intra-gender Speaker Verification" in APSIPA ASC, 2023
29 International Journal Hyungchan Yoon, Changhwan Kim, Seyun Um, Hyun-Wook Yoon, Hong-Goo Kang "SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech Systems" in IEEE Signal Processing Letters, vol.30, pp.593-597, 2023