{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:35:02Z","timestamp":1742942102381,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819980697"},{"type":"electronic","value":"9789819980703"}],"license":[{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8070-3_28","type":"book-chapter","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T08:02:54Z","timestamp":1699948974000},"page":"367-379","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Sound Local and\u00a0Global Features for\u00a0Language-Queried Target Sound Extraction"],"prefix":"10.1007","author":[{"given":"Xinmeng","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiping","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,15]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Chen, K., Du, X., Zhu, B., Ma, Z., Berg-Kirkpatrick, T., Dubnov, S.: Zero-shot audio source separation through query-based learning from weakly-labeled data. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 4441\u20134449 (2022)","DOI":"10.1609\/aaai.v36i4.20366"},{"issue":"5","key":"28_CR2","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1121\/1.1907229","volume":"25","author":"EC Cherry","year":"1953","unstructured":"Cherry, E.C.: Some experiments on the recognition of speech, with one and with two ears. J. Acoust. Soc. Am. 25(5), 975\u2013979 (1953)","journal-title":"J. Acoust. Soc. Am."},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"28_CR4","doi-asserted-by":"publisher","unstructured":"Delcroix, M., V\u00e1zquez, J.B., Ochiai, T., Kinoshita, K., Araki, S.: Few-shot learning of new sound classes for target sound extraction. In: Proceedings of Interspeech 2021, pp. 3500\u20133504 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-1369","DOI":"10.21437\/Interspeech.2021-1369"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"28_CR6","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"28_CR7","unstructured":"Kim, C.D., Kim, B., Lee, H., Kim, G.: Audiocaps: generating captions for audios in the wild. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 119\u2013132 (2019)"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 510\u2013519 (2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"28_CR9","doi-asserted-by":"publisher","unstructured":"Liu, X., et al.: Separate what you describe: language-queried audio source separation. In: Proceedings of Interspeech 2022, pp. 1801\u20131805 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10894","DOI":"10.21437\/Interspeech.2022-10894"},{"issue":"8","key":"28_CR10","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","volume":"27","author":"Y Luo","year":"2019","unstructured":"Luo, Y., Mesgarani, N.: Conv-tasnet: surpassing ideal time-frequency magnitude masking for speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(8), 1256\u20131266 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"28_CR11","unstructured":"Mesaros, A., Heittola, T., Virtanen, T.: A multi-device dataset for urban acoustic scene classification. In: Scenes and Events 2018 Workshop (DCASE 2018), p. 9 (2018)"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Ohishi, Y., et al.: Conceptbeam: concept driven target speech extraction. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4252\u20134260 (2022)","DOI":"10.1145\/3503161.3548397"},{"key":"28_CR13","doi-asserted-by":"publisher","first-page":"3032","DOI":"10.1109\/TASLP.2022.3205759","volume":"30","author":"Z Pan","year":"2022","unstructured":"Pan, Z., Ge, M., Li, H.: USEV: universal speaker extraction with visual cue. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 3032\u20133045 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Pandey, A., Wang, D.: Densely connected neural network with dilated convolutions for real-time speech enhancement in the time domain. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6629\u20136633. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"28_CR15","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Salamon, J., MacConnell, D., Cartwright, M., Li, P., Bello, J.P.: Scaper: a library for soundscape synthesis and augmentation. In: 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 344\u2013348. IEEE (2017)","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Slizovskaia, O., Kim, L., Haro, G., Gomez, E.: End-to-end sound source separation conditioned on instrument labels. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 306\u2013310. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683800"},{"key":"28_CR19","unstructured":"Stoller, D., Ewert, S., Dixon, S.: Wave-u-net: a multi-scale neural network for end-to-end audio source separation. arXiv preprint arXiv:1806.03185 (2018)"},{"key":"28_CR20","unstructured":"Turc, I., Chang, M.W., Lee, K., Toutanova, K.: Well-read students learn better: on the importance of pre-training compact models. arXiv preprint arXiv:1908.08962 (2019)"},{"key":"28_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Veluri, B., Chan, J., Itani, M., Chen, T., Yoshioka, T., Gollakota, S.: Real-time target sound extraction. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10094573"},{"issue":"4","key":"28_CR23","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent, E., Gribonval, R., F\u00e9votte, C.: Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462\u20131469 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"28_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-58548-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., Chen, L.-C.: Axial-DeepLab: stand-alone axial-attention for panoptic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 108\u2013126. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_7"},{"key":"28_CR25","doi-asserted-by":"publisher","unstructured":"Xu, X., Hao, J.: U-Former: improving monaural speech enhancement with multi-head self and cross attention. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 663\u2013369 (2022). https:\/\/doi.org\/10.1109\/ICPR56361.2022.9956638","DOI":"10.1109\/ICPR56361.2022.9956638"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Xu, X., Tu, W., Yang, Y.: Selector-enhancer: learning dynamic selection of local and non-local attention operation for speech enhancement. In: Proceedings of the AAAI Conference on Artificial Intelligence (2023)","DOI":"10.1609\/aaai.v37i11.26622"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Yu, G., Li, A., Zheng, C., Guo, Y., Wang, Y., Wang, H.: Dual-branch attention-in-attention transformer for single-channel speech enhancement. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7847\u20137851. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746273"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8070-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:25:43Z","timestamp":1710260743000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8070-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,15]]},"ISBN":["9789819980697","9789819980703"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8070-3_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,11,15]]},"assertion":[{"value":"15 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"650","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"51% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.14","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.46","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}