{"type":"ScholarlyArticle","title":"Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction","authors":[{"name":"Zhaoxi Mu","slug":"zhaoxi-mu","given":"Zhaoxi","family":"Mu","affiliation":"Jiaotong University"},{"name":"Xinyu Yang","slug":"xinyu-yang","given":"Xinyu","family":"Yang","affiliation":""}],"abstract":"The integration of visual cues has revitalized the performance of the target speech extraction task, elevating it to the forefront of the field. Nevertheless, this multi-modal learning paradigm often encounters the challenge of modality imbalance. In audio-visual target speech extraction tasks, the audio modality tends to dominate, potentially overshadowing the importance of visual guidance. To tackle this issue, we propose AVSepChain, drawing inspiration from the speech chain concept. Our approach partitions the audio-visual target speech extraction task into two stages: speech perception and speech production. In the speech perception stage, audio serves as the dominant modality, while visual information acts as the conditional modality. Conversely, in the speech production stage, the roles are reversed. This transformation of modality status aims to alleviate the problem of modality imbalance. Additionally, we introduce a contrastive semantic matching loss to ensure that the semantic information conveyed by the generated speech aligns with the semantic information conveyed by lip movements during the speech production stage. Through extensive experiments conducted on multiple benchmark datasets for audio-visual target speech extraction, we showcase the superior performance achieved by our proposed method.","doi":"10.24963/ijcai.2024/709","url":"https://ijcai.org/proceedings/2024/709","pdf":"https://ijcai.org/proceedings/2024/0709.pdf","markdown":"https://ijcai.org/proceedings/2024/709.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/709","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Natural Language Processing","track":"Main Track","number":709,"pages":{"first":6415,"last":6423},"keywords":["Machine Learning: ML: Multi-modal learning","Natural Language Processing: NLP: Speech"],"videos":[],"references":[{"position":1,"raw":"[Afouras et al., 2018a] Triantafyllos Afouras, Joon Son Chung, and Andrew Zisserman. The conversation: Deep audio-visual speech enhancement. In INTERSPEECH, pages 3244-3248. ISCA, 2018.","title":"The conversation: Deep audio-visual speech enhancement","authors":"Afouras","year":"2018","venue":"INTERSPEECH","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Afouras et al., 2018b] Triantafyllos Afouras, Joon Son Chung, and Andrew Zisserman. LRS3-TED: a large- scale dataset for visual speech recognition. CoRR, abs/1809.00496, 2018.","title":"LRS3-TED: a largescale dataset for visual speech recognition","authors":"Afouras","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Afouras et al., 2022] Triantafyllos Afouras, Joon Son Chung, Andrew W. Senior, Oriol Vinyals, and Andrew Zisserman. Deep audio-visual speech recognition. IEEE Trans. Pattern Anal. Mach. Intell., 44(12):8717-8727, 2022.","title":"Deep audio-visual speech recognition","authors":"Afouras","year":"2022","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bear and Harvey, 2017] Helen L. Bear and Richard W. Har- vey. Phoneme-to-viseme mappings: the good, the bad, and the ugly. Speech Commun., 95:40-67, 2017.","title":"Phoneme-to-viseme mappings: the good, the bad, and the ugly","authors":"Helen L Bear, Richard W Harvey","year":"2017","venue":"Speech Commun","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bronkhorst, 2000] Adelbert W Bronkhorst. The cocktail party phenomenon: A review of research on speech intelli- gibility in multiple-talker conditions. Acta Acustica united with Acustica, 86(1):117-128, 2000.","title":"The cocktail party phenomenon: A review of research on speech intelligibility in multiple-talker conditions","authors":"W Adelbert, Bronkhorst","year":"2000","venue":"Acta Acustica united with Acustica","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Choi et al., 2023a] Jeongsoo Choi, Joanna Hong, and Yong Man Ro. Diffv2s: Diffusion-based video-to-speech synthesis with vision-guided speaker embedding. CoRR, abs/2308.07787, 2023.","title":"Diffv2s: Diffusion-based video-to-speech synthesis with vision-guided speaker embedding","authors":"Choi","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Choi et al., 2023b] Jeongsoo Choi, Minsu Kim, and Yong Man Ro. Intelligible lip-to-speech synthesis with speech units. CoRR, abs/2305.19603, 2023.","title":"Intelligible lip-to-speech synthesis with speech units","authors":"Choi","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chung et al., 2018] Joon Son Chung, Arsha Nagrani, and Andrew Zisserman. Voxceleb2: Deep speaker recognition. In INTERSPEECH, pages 1086-1090. ISCA, 2018.","title":"Voxceleb2: Deep speaker recognition","authors":"Son Joon, Arsha Chung, Andrew Nagrani, Zisserman","year":"2018","venue":"INTERSPEECH","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[de Mira et al., 2022] Rodrigo Schoburg Carrillo de Mira, Alexandros Haliassos, Stavros Petridis, Björn W. Schuller, and Maja Pantic. SVTS: scalable video-to-speech synthe- sis. In INTERSPEECH, pages 1836-1840. ISCA, 2022.","title":"SVTS: scalable video-to-speech synthesis","authors":"Mira De","year":"2022","venue":"INTERSPEECH","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Deller Jr, 1993] John R Deller Jr. Discrete-time processing of speech signals. In Discrete-time processing of speech signals, pages 908-908. 1993.","title":"Discrete-time processing of speech signals","authors":"John R Deller Jr","year":"1993","venue":"Discrete-time processing of speech signals","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Denes and Pinson, 1993] Peter B Denes and Elliot Pinson. The speech chain. Macmillan, 1993.","title":"The speech chain","authors":"B Peter, Elliot Denes, Pinson","year":"1993","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Du et al., 2021] Chenzhuang Du, Tingle Li, Yichen Liu, Zixin Wen, Tianyu Hua, Yue Wang, and Hang Zhao. Im- proving multi-modal learning with uni-modal teachers. CoRR, abs/2106.11059, 2021.","title":"Improving multi-modal learning with uni-modal teachers","authors":"Chenzhuang Du, Tingle Li, Yichen Liu, Zixin Wen, Tianyu Hua, Yue Wang, Hang Zhao","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ephrat et al., 2018] Ariel Ephrat, Inbar Mosseri, Oran Lang, Tali Dekel, Kevin Wilson, Avinatan Hassidim, William T. Freeman, and Michael Rubinstein. Looking to listen at the cocktail party: a speaker-independent audio- visual model for speech separation. ACM Trans. Graph., 37(4):112, 2018.","title":"Looking to listen at the cocktail party: a speaker-independent audiovisual model for speech separation","authors":"Ariel Ephrat, Inbar Mosseri, Oran Lang, Tali Dekel, Kevin Wilson, Avinatan Hassidim, William T Freeman, Michael Rubinstein","year":"2018","venue":"ACM Trans. Graph","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Fan et al., 2023] Yunfeng Fan, Wenchao Xu, Haozhao Wang, Junxiao Wang, and Song Guo. PMR: prototypical modal rebalance for multimodal learning. In CVPR, pages 20029-20038. IEEE, 2023.","title":"PMR: prototypical modal rebalance for multimodal learning","authors":"Yunfeng Fan, Wenchao Xu, Haozhao Wang, Junxiao Wang, Song Guo","year":"2023","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Fu et al., 2023] Jie Fu, Junyu Gao, and Changsheng Xu. Multimodal imbalance-aware gradient modulation for weakly-supervised audio-visual video parsing. CoRR, abs/2307.02041, 2023.","title":"Multimodal imbalance-aware gradient modulation for weakly-supervised audio-visual video parsing","authors":"Fu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Gao and Grauman, 2021] Ruohan Gao and Kristen Grau- man. Visualvoice: Audio-visual speech separation with cross-modal consistency. In CVPR, pages 15495-15505.","title":"Visualvoice: Audio-visual speech separation with cross-modal consistency","authors":"Grauman ; Gao, Kristen Gao, Grauman","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ge et al., 2020] Meng Ge, Chenglin Xu, Longbiao Wang, Eng Siong Chng, Jianwu Dang, and Haizhou Li. Spex+: A complete time domain speaker extraction network. In INTERSPEECH, pages 1406-1410. ISCA, 2020.","title":"Spex+: A complete time domain speaker extraction network","authors":"Meng Ge, Chenglin Xu, Longbiao Wang, Eng Siong Chng, Jianwu Dang, Haizhou Li","year":"2020","venue":"INTERSPEECH","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Harte and Gillen, 2015] Naomi Harte and Eoin Gillen. TCD-TIMIT: an audio-visual corpus of continuous speech. IEEE Trans. Multim., 17(5):603-615, 2015.","title":"TCD-TIMIT: an audio-visual corpus of continuous speech","authors":"Gillen Harte, Naomi Harte, Eoin Gillen","year":"2015","venue":"IEEE Trans. Multim","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Hsu et al., 2021] Wei-Ning Hsu, Benjamin Bolte, Yao- Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhut- dinov, and Abdelrahman Mohamed. Hubert: Self- supervised speech representation learning by masked pre- diction of hidden units. IEEE ACM Trans. Audio Speech Lang. Process., 29:3451-3460, 2021.","title":"Hubert: Selfsupervised speech representation learning by masked prediction of hidden units","authors":"Wei-Ning Hsu, Benjamin Bolte, Hubert Yao-Hung, Kushal Tsai, Ruslan Lakhotia, Abdelrahman Salakhutdinov, Mohamed","year":"2021","venue":"IEEE ACM Trans. Audio Speech Lang. Process","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Kim et al., 2021] Minsu Kim, Joanna Hong, and Yong Man Ro. Lip to speech synthesis with visual context attentional GAN. In NeurIPS, pages 2758-2770, 2021.","title":"Lip to speech synthesis with visual context attentional GAN","authors":"Minsu Kim, Joanna Hong, Yong Man Ro","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Kim et al., 2023] Minsu Kim, Joanna Hong, and Yong Man Ro. Lip-to-speech synthesis in the wild with multi-task learning. CoRR, abs/2302.08841, 2023.","title":"Lip-to-speech synthesis in the wild with multi-task learning","authors":"Minsu Kim, Joanna Hong, Yong Man Ro","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lee et al., 2023] Suyeon Lee, Chaeyoung Jung, Youngjoon Jang, Jaehun Kim, and Joon Son Chung. Seeing through the conversation: Audio-visual speech separation based on diffusion model. CoRR, abs/2310.19581, 2023.","title":"Seeing through the conversation: Audio-visual speech separation based on diffusion model","authors":"Lee","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Li et al., 2018] Yuanqing Li, Fangyi Wang, Yongbin Chen, Andrzej Cichocki, and Terrence Sejnowski. The effects of audiovisual inputs on solving the cocktail party prob- lem in the human brain: An fmri study. Cerebral Cortex, 28(10):3623-3637, 2018.","title":"The effects of audiovisual inputs on solving the cocktail party problem in the human brain: An fmri study","authors":"Yuanqing Li, Fangyi Wang, Yongbin Chen, Andrzej Cichocki, Terrence Sejnowski","year":"2018","venue":"Cerebral Cortex","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Li et al., 2022] Kai Li, Fenghua Xie, Hang Chen, Kexin Yuan, and Xiaolin Hu. An audio-visual speech separation model inspired by cortico-thalamo-cortical circuits. CoRR, abs/2212.10744, 2022.","title":"An audio-visual speech separation model inspired by cortico-thalamo-cortical circuits","authors":"Kai Li, Fenghua Xie, Hang Chen, Kexin Yuan, Xiaolin Hu","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Lin et al., 2023] Jiuxin Lin, Xinyu Cai, Heinrich Dinkel, Jun Chen, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Zhiyong Wu, Yujun Wang, and Helen Meng. Av- sepformer: Cross-attention sepformer for audio-visual tar- get speaker extraction. CoRR, abs/2306.14170, 2023.","title":"Avsepformer: Cross-attention sepformer for audio-visual target speaker extraction","authors":"Jiuxin Lin, Xinyu Cai, Heinrich Dinkel, Jun Chen, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Zhiyong Wu, Yujun Wang, Helen Meng","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Luo et al., 2023] Simian Luo, Chuanhao Yan, Chenxu Hu, and Hang Zhao. Diff-foley: Synchronized video-to- audio synthesis with latent diffusion models. CoRR, abs/2306.17203, 2023.","title":"Diff-foley: Synchronized video-toaudio synthesis with latent diffusion models","authors":"Luo","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Lutati et al., 2023] Shahar Lutati, Eliya Nachmani, and Lior Wolf. Separate and diffuse: Using a pretrained dif- fusion model for improving source separation. CoRR, abs/2301.10752, 2023.","title":"Separate and diffuse: Using a pretrained diffusion model for improving source separation","authors":"Shahar Lutati, Eliya Nachmani, Lior Wolf","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Martínez et al., 2020] Brais Martínez, Pingchuan Ma, Stavros Petridis, and Maja Pantic. Lipreading using temporal convolutional networks. In ICASSP, pages 6319-6323. IEEE, 2020.","title":"Lipreading using temporal convolutional networks","authors":"Brais Martínez, Pingchuan Ma, Stavros Petridis, Maja Pantic","year":"2020","venue":"ICASSP","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Massaro and Simpson, 2014] Dominic W Massaro and Jef- fry A Simpson. Speech perception by ear and eye: A paradigm for psychological inquiry. Psychology Press, 2014.","title":"Speech perception by ear and eye: A paradigm for psychological inquiry","authors":"Dominic W Massaro, Jeffry A Simpson","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Mu et al., 2021] Zhaoxi Mu, Xinyu Yang, and Yizhuo Dong. Review of end-to-end speech synthesis technology based on deep learning. CoRR, abs/2104.09995, 2021.","title":"Review of end-to-end speech synthesis technology based on deep learning","authors":"Mu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Mu et al., 2023] Zhaoxi Mu, Xinyu Yang, Sining Sun, and Qing Yang. Self-supervised disentangled representa- tion learning for robust target speech extraction. CoRR, abs/2312.10305, 2023.","title":"Self-supervised disentangled representation learning for robust target speech extraction","authors":"Mu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Ochiai et al., 2019] Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Atsunori Ogawa, and Tomohiro Nakatani. Multimodal speakerbeam: Single channel target speech extraction with audio-visual speaker clues. In INTERSPEECH, pages 2718-2722. ISCA, 2019.","title":"Multimodal speakerbeam: Single channel target speech extraction with audio-visual speaker clues","authors":"Ochiai","year":"2019","venue":"INTERSPEECH","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Pan et al., 2021] Zexu Pan, Ruijie Tao, Chenglin Xu, and Haizhou Li. Muse: Multi-modal target speaker extrac- tion with visual cues. In ICASSP, pages 6678-6682. IEEE, 2021.","title":"Muse: Multi-modal target speaker extraction with visual cues","authors":"Pan","year":"2021","venue":"ICASSP","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Prajwal et al., 2020] K. R. Prajwal, Rudrabha Mukhopad- hyay, Vinay P. Namboodiri, and C. V. Jawahar. Learning individual speaking styles for accurate lip to speech syn- thesis. In CVPR, pages 13793-13802. Computer Vision Foundation / IEEE, 2020.","title":"Learning individual speaking styles for accurate lip to speech synthesis","authors":"K R Prajwal, Rudrabha Mukhopadhyay, P Vinay, C V Namboodiri, Jawahar","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Rix et al., 2001] Antony W. Rix, John G. Beerends, Michael P. Hollier, and Andries P. Hekstra. Percep- tual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs. In ICASSP, pages 749-752. IEEE, 2001.","title":"Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs","authors":"Antony W Rix, John G Beerends, Michael P Hollier, Andries P Hekstra","year":"2001","venue":"ICASSP","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Roux et al., 2019] Jonathan Le Roux, Scott Wisdom, Hakan Erdogan, and John R. Hershey. SDR -half-baked or well done? In ICASSP, pages 626-630. IEEE, 2019.","title":"SDR -half-baked or well done?","authors":"Jonathan Le Roux, Scott Wisdom, Hakan Erdogan, John R Hershey","year":"2019","venue":"ICASSP","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Shi et al., 2022a] Bowen Shi, Wei-Ning Hsu, Kushal Lakhotia, and Abdelrahman Mohamed. Learning audio- visual speech representation by masked multimodal clus- ter prediction. In ICLR. OpenReview.net, 2022.","title":"Learning audiovisual speech representation by masked multimodal cluster prediction","authors":"Shi","year":"2022","venue":"ICLR. OpenReview.net","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Shi et al., 2022b] Bowen Shi, Wei-Ning Hsu, and Abdel- rahman Mohamed. Robust self-supervised audio-visual speech recognition. In INTERSPEECH, pages 2118-2122. ISCA, 2022.","title":"Robust self-supervised audio-visual speech recognition","authors":"Shi","year":"2022","venue":"INTERSPEECH","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Shi et al., 2022c] Bowen Shi, Wei-Ning Hsu, and Abdel- rahman Mohamed. Robust self-supervised audio-visual speech recognition. In INTERSPEECH, pages 2118-2122. ISCA, 2022.","title":"Robust self-supervised audio-visual speech recognition","authors":"Shi","year":"2022","venue":"INTERSPEECH","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Stenzel et al., 2019] Hanne Stenzel, Jon Francombe, and Philip JB Jackson. Limits of perceived audio-visual spa- tial coherence as defined by reaction time measurements. Frontiers in neuroscience, 13:451, 2019.","title":"Limits of perceived audio-visual spatial coherence as defined by reaction time measurements","authors":"Hanne Stenzel, Jon Francombe, Philip Jb Jackson","year":"2019","venue":"Frontiers in neuroscience","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Subakan et al., 2021] Cem Subakan, Mirco Ravanelli, Samuele Cornell, Mirko Bronzi, and Jianyuan Zhong. Attention is all you need in speech separation. In ICASSP, pages 21-25. IEEE, 2021.","title":"Attention is all you need in speech separation","authors":"Subakan","year":"2021","venue":"ICASSP","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NIPS, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Vincent et al., 2006] Emmanuel Vincent, Rémi Gribonval, and Cédric Févotte. Performance measurement in blind audio source separation. IEEE Trans. Speech Audio Pro- cess., 14(4):1462-1469, 2006.","title":"Performance measurement in blind audio source separation","authors":"Emmanuel Vincent, Rémi Gribonval, Cédric Févotte","year":"2006","venue":"IEEE Trans. Speech Audio Process","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Wu et al., 2019] Jian Wu, Yong Xu, Shi-Xiong Zhang, Lianwu Chen, Meng Yu, Lei Xie, and Dong Yu. Time domain audio visual speech separation. In ASRU, pages 667-673. IEEE, 2019.","title":"Time domain audio visual speech separation","authors":"Jian Wu, Yong Xu, Shi-Xiong Zhang, Lianwu Chen, Meng Yu, Lei Xie, Dong Yu","year":"2019","venue":"ASRU","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Wu et al., 2022] Nan Wu, Stanislaw Jastrzebski, Kyunghyun Cho, and Krzysztof J. Geras. Character- izing and overcoming the greedy nature of learning in multi-modal deep neural networks. In ICML, volume 162 of Proceedings of Machine Learning Research, pages 24043-24055.","title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","authors":"Nan Wu, Stanislaw Jastrzebski, Kyunghyun Cho, Krzysztof J Geras","year":null,"venue":"Proceedings of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"PMLR, 2022.","title":null,"authors":"Pmlr","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Xu et al., 2020] Chenglin Xu, Wei Rao, Eng Siong Chng, and Haizhou Li. Spex: Multi-scale time domain speaker extraction network. IEEE ACM Trans. Audio Speech Lang. Process., 28:1370-1384, 2020.","title":"Spex: Multi-scale time domain speaker extraction network","authors":"Chenglin Xu, Wei Rao, Eng Siong Chng, Haizhou Li","year":"2020","venue":"IEEE ACM Trans. Audio Speech Lang. Process","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Zhou et al., 2022] Dongzhan Zhou, Xinchi Zhou, Di Hu, Hang Zhou, Lei Bai, Ziwei Liu, and Wanli Ouyang. Sep- fusion: Finding optimal fusion structures for visual sound separation. In AAAI, pages 3544-3552. AAAI Press, 2022.","title":"Sepfusion: Finding optimal fusion structures for visual sound separation","authors":"Dongzhan Zhou, Xinchi Zhou, Di Hu, Hang Zhou, Lei Bai, Ziwei Liu, Wanli Ouyang","year":"2022","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}