Seeing Voices and Hearing Voices: Learning Discriminative Embeddings Using Cross-Modal Self-Supervision

International Conference
2020-10-01 16:54
Authors : Soo-Whan Chung, Hong-Goo Kang, Joon Son Chung

Year : 2020

Publisher / Conference : INTERSPEECH

The goal of this work is to train discriminative cross-modal embeddings without access to manually annotated data. Recent advances in self-supervised learning have shown that effective representations can be learnt from natural cross-modal synchrony. We build on earlier work to train embeddings that are more discriminative for uni-modal downstream tasks. To this end, we propose a novel training strategy that not only optimises metrics across modalities, but also enforces intra-class feature separation within each of the modalities. The effectiveness of the method is demonstrated on two downstream tasks: lip reading using the features trained on audio-visual synchronisation, and speaker recognition using the features trained for cross-modal biometric matching. The proposed method outperforms state-of-the-art self-supervised baselines by a significant margin.
전체 355
112 International Conference Min-Jae Hwang, Frank Soong, Eunwoo Song, Xi Wang, Hyeonjoo Kang, Hong-Goo Kang "LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis" in APSIPA, 2020
111 International Conference Hyungseob Lim, Suhyeon Oh, Kyungguen Byun, Hong-Goo Kang "A Study on Conditional Features for a Flow-based Neural Vocoder" in Asilomar Conference on Signals, Systems, and Computers, 2020
110 International Conference Soo-Whan Chung, Soyeon Choe, Joon Son Chung, Hong-Goo Kang "FaceFilter: Audio-visual speech separation using still images" in INTERSPEECH (*awarded Best Student Paper), 2020
109 International Conference Soo-Whan Chung, Hong-Goo Kang, Joon Son Chung "Seeing Voices and Hearing Voices: Learning Discriminative Embeddings Using Cross-Modal Self-Supervision" in INTERSPEECH, 2020
108 International Conference Hyewon Han, Soo-Whan Chung, Hong-Goo Kang "MIRNet: Learning multiple identities representations in overlapped speech" in INTERSPEECH, 2020
107 International Conference Yoohwan Kwon, Soo-Whan Chung, Hong-Goo Kang "Intra-Class Variation Reduction of Speaker Representation in Disentanglement Framework" in INTERSPEECH, 2020
106 International Conference Minh-Tri Ho, Jinyoung Lee, Bong-Ki Lee, Dong Hoon Yi, Hong-Goo Kang "A Cross-channel Attention-based Wave-U-Net for Multi-channel Speech Enhancement" in INTERSPEECH, 2020
105 International Conference Seyun Um, Sangshin Oh, Kyungguen Byun, Inseon Jang, ChungHyun Ahn, Hong-Goo Kang "Emotional Speech Synthesis with Rich and Granularized Control" in ICASSP, 2020
104 International Conference Min-Jae Hwang, Eunwoo Song, Ryuichi Yamamoto, Frank Soong, Hong-Goo Kang "Improving LPCNet-based Text-to-Speech with Linear Prediction-structured Mixture Density Network" in ICASSP, 2020
103 International Conference Hyeonjoo Kang, Young-Sun Joo, Inseon Jang, Chunghyun Ahn, Hong-Goo Kang "A Study on Acoustic Parameter Selection Strategies to Improve Deep Learning-Based Speech Synthesis" in APSIPA, 2019