Papers

Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation

International Conference
2021~
작성자
한혜원
작성일
2021-07-01 17:05
조회
613
Authors : Jiyoung Lee*, Soo-Whan Chung*, Sunok Kim, Hong-Goo Kang**, Kwanghoon Sohn**

Year : 2021

Publisher / Conference : CVPR

Research area : Audio-Visual, Source Separation


Presentation : Poster

In this paper, we address the problem of separating individual speech signals from videos using audio-visual neural processing. Most conventional approaches utilize frame-wise matching criteria to extract shared information between audio and video signals; thus, their performance heavily depends on the accuracy of audio-visual synchronization and the effectiveness of their representations. To overcome the frame discontinuity problem between two modalities due to transmission delay mismatch or jitter, we propose a cross-modal affinity network (CaffNet) that learns global correspondence as well as locally-varying affinities between audio and visual streams. Since the global term provides stability over a temporal sequence at the utterance-level, this also resolves a label permutation problem characterized by inconsistent assignments. By introducing a complex convolution network, CaffNet-C, that estimates both magnitude and phase representations in the time-frequency domain, we further improve the separation performance. Experimental results verify that the proposed methods outperform conventional ones on various datasets, demonstrating their advantages in real-world scenarios.


Notes
*Jiyoung Lee and Soo-Whan Chung contributed equally to this work.
**Hong-Goo Kang and Kwanghoon Sohn are co-corresponding authors.
전체 327
317 International Conference Zainab Alhakeem, Yoohwan Kwon, Hong-Goo Kang "Disentangled Representations for Arabic Dialect Identification based on Supervised Clustering with Triplet Loss" in EUSIPCO, 2021
316 International Conference Miseul Kim, Minh-Tri Ho, Hong-Goo Kang "Self-supervised Complex Network for Machine Sound Anomaly Detection" in EUSIPCO, 2021
315 International Conference Kihyuk Jeong, Huu-Kim Nguyen, Hong-Goo Kang "A Fast and Lightweight Text-To-Speech Model with Spectrum and Waveform Alignment Algorithms" in EUSIPCO, 2021
314 International Conference Jiyoung Lee*, Soo-Whan Chung*, Sunok Kim, Hong-Goo Kang**, Kwanghoon Sohn** "Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation" in CVPR, 2021
313 International Conference Zainab Alhakeem, Hong-Goo Kang "Confidence Learning from Noisy Labels for Arabic Dialect Identification" in ITC-CSCC, 2021
312 International Conference Huu-Kim Nguyen, Kihyuk Jeong, Hong-Goo Kang "Fast and Lightweight Speech Synthesis Model based on FastSpeech2" in ITC-CSCC, 2021
311 International Conference Yoohwan Kwon*, Hee-Soo Heo*, Bong-Jin Lee, Joon Son Chung "The ins and outs of speaker recognition: lessons from VoxSRC 2020" in ICASSP, 2021
310 International Conference You Jin Kim, Hee Soo Heo, Soo-Whan Chung, Bong-Jin Lee "End-to-end Lip Synchronisation Based on Pattern Classification" in IEEE Spoken Language Technology Workshop (SLT), 2020
309 International Conference Seong Min Kye, Yoohwan Kwon, Joon Son Chung "Cross Attentive Pooling for Speaker Verification" in IEEE Spoken Language Technology Workshop (SLT), 2020
308 International Conference Suhyeon Oh, Hyungseob Lim, Kyungguen Byun, Min-Jae Hwang, Eunwoo Song, Hong-Goo Kang "ExcitGlow: Improving a WaveGlow-based Neural Vocoder with Linear Prediction Analysis" in APSIPA (*awarded Best Paper), 2020