{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:20:38Z","timestamp":1775067638622,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"A*STAR Center for Frontier Artificial Intelligence Research"},{"name":"Data Science and Artificial Intelligence Research Centre, School of Computer Science and Engineering at the Nanyang Technological University, Singapore"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591876","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"2701-2711","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Towards Building Voice-based Conversational Recommender Systems: Datasets, Potential Solutions and Prospects"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8072-2019","authenticated-orcid":false,"given":"Xinghua","family":"Qu","sequence":"first","affiliation":[{"name":"Bytedance AI Lab, Singapore, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4201-1934","authenticated-orcid":false,"given":"Hongyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Bytedance AI Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3350-7022","authenticated-orcid":false,"given":"Zhu","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing, Centre for Frontier AI Research, A*STAR, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1324-4277","authenticated-orcid":false,"given":"Xiang","family":"Yin","sequence":"additional","affiliation":[{"name":"Bytedance AI Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-169X","authenticated-orcid":false,"given":"Yew Soon","family":"Ong","sequence":"additional","affiliation":[{"name":"A*STAR Centre for Frontier AI Research & Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1311-9097","authenticated-orcid":false,"given":"Lu","family":"Lu","sequence":"additional","affiliation":[{"name":"Bytedance AI Lab, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5508-1328","authenticated-orcid":false,"given":"Zejun","family":"Ma","sequence":"additional","affiliation":[{"name":"Bytedance AI Lab, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1189"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_2_3_1","volume-title":"Unsupervised cross-lingual representation learning for speech recognition. arXiv preprint arXiv:2006.13979","author":"Conneau Alexis","year":"2020","unstructured":"Alexis Conneau, Alexei Baevski, Ronan Collobert, Abdelrahman Mohamed, and Michael Auli. 2020. Unsupervised cross-lingual representation learning for speech recognition. arXiv preprint arXiv:2006.13979 (2020)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462913"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of International Conference on Learning Representations (ICLR).","author":"Donahue Chris","year":"2019","unstructured":"Chris Donahue, Julian McAuley, and Miller Puckette. 2019. Adversarial Audio Synthesis. In Proceedings of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463247"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.06.002"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.654"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531844"},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the 6th Italian Conference on Computational Linguistics (CLiC-it).","author":"Iovine Andrea","year":"2019","unstructured":"Andrea Iovine, Fedelucio Narducci, and Marco de Gemmis. 2019. A Dataset of Real Dialogues for Conversational Recommender Systems.. In Proceedings of the 6th Italian Conference on Computational Linguistics (CLiC-it)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453154"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1203"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109873"},{"key":"e_1_3_2_2_15_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"30","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems (NeurIPS), Vol. 30 (2017)."},{"key":"e_1_3_2_2_16_1","volume-title":"International Conference on Machine Learning (ICML). 5530--5540","author":"Kim Jaehyeon","year":"2021","unstructured":"Jaehyeon Kim, Jungil Kong, and Juhee Son. 2021. Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In International Conference on Machine Learning (ICML). 5530--5540."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371769"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403258"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"e_1_3_2_2_20_1","volume-title":"Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal.","author":"Li Raymond","year":"2018","unstructured":"Raymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal. 2018. Towards deep conversational recommendations. Advances in Neural Information Processing Systems (NeurIPS), Vol. 31 (2018)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532074"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.98"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474600"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sigdial-1.28"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1081"},{"key":"e_1_3_2_2_26_1","volume-title":"Advances in Artificial Intelligence: 17th International Conference of the Italian Association for Artificial Intelligence (AI* IA). 528--538","author":"Narducci Fedelucio","year":"2018","unstructured":"Fedelucio Narducci, Marco de Gemmis, Pasquale Lops, and Giovanni Semeraro. 2018. Improving the user experience with a conversational recommender system. In Advances in Artificial Intelligence: 17th International Conference of the Italian Association for Artificial Intelligence (AI* IA). 528--538."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Daniel Nettle Suzanne Romaine et al. 2000. Vanishing voices: The extinction of the world's languages. Oxford University Press on Demand.","DOI":"10.1093\/oso\/9780195136241.001.0001"},{"key":"e_1_3_2_2_28_1","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. arXiv preprint arXiv:2203.02155 (2022)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462839"},{"key":"e_1_3_2_2_30_1","volume-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech. arXiv preprint arXiv:2006.04558","author":"Ren Yi","year":"2020","unstructured":"Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2020. Fastspeech 2: Fast and high-quality end-to-end text to speech. arXiv preprint arXiv:2006.04558 (2020)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532077"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210002"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531830"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539382"},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL). 438--449","author":"Wen Tsung-Hsien","year":"2016","unstructured":"Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M Rojas-Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. 2016. A network-based end-to-end trainable task-oriented dialogue system. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL). 438--449."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1356"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.463"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441791"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412719"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146443"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401164"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380148"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512088"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557482"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.36"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.365"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498514"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531852"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591876","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:38:07Z","timestamp":1750178287000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591876"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":52,"alternative-id":["10.1145\/3539618.3591876","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591876","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}