{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T09:30:27Z","timestamp":1768210227881,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539030","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:12Z","timestamp":1660331172000},"page":"3040-3050","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["DuIVA: An Intelligent Voice Assistant for Hands-free and Eyes-free Voice Interaction with the Baidu Maps App"],"prefix":"10.1145","author":[{"given":"Jizhou","family":"Huang","sequence":"first","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"given":"Haifeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"given":"Shiqiang","family":"Ding","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"given":"Shaolei","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Dealing with ill-formed English text. The computational analysis of English: a corpus-based approach","author":"Atwell Eric S","year":"1987","unstructured":"Eric S Atwell and Stephen Elliot. 1987. Dealing with ill-formed English text. The computational analysis of English: a corpus-based approach (1987), 120--138."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3166054.3166058"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Miao Fan Yibo Sun Jizhou Huang Haifeng Wang and Ying Li. 2021. Meta-Learned Spatial-Temporal POI Auto-Completion for the Search Engine at Baidu Maps. In KDD. 2822--2830.","DOI":"10.1145\/3447548.3467058"},{"key":"e_1_3_2_2_4_1","volume-title":"SSML: Self-Supervised Meta-Learner for En Route Travel Time Estimation at Baidu Maps. In KDD. 2840--2848.","author":"Fang Xiaomin","year":"2021","unstructured":"Xiaomin Fang, Jizhou Huang, Fan Wang, Lihang Liu, Yibo Sun, and Haifeng Wang. 2021. SSML: Self-Supervised Meta-Learner for En Route Travel Time Estimation at Baidu Maps. In KDD. 2840--2848."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Xiaomin Fang Jizhou Huang Fan Wang Lingke Zeng Haijin Liang and Haifeng Wang. 2020. ConSTGAT: Contextual Spatial-Temporal Graph Attention Network for Travel Time Estimation at Baidu Maps. In KDD. 2697--2705.","DOI":"10.1145\/3394486.3403320"},{"key":"e_1_3_2_2_6_1","unstructured":"Gregory M Fitch Susan A Soccolich Feng Guo Julie McClafferty et al. 2013. The Impact of Hand-Held and Hands-Free Cell Phone Use on Driving Performance and Safety-Critical Event Risk. Technical Report."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"David Goddeau Helen Meng Joseph Polifroni Stephanie Seneff and Senis Busayapongchai. 1996. A form-based dialogue manager for spoken language applications. In ICSLP. 701--704.","DOI":"10.1109\/ICSLP.1996.607458"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2010.10.003"},{"key":"e_1_3_2_2_9_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard A.","year":"2017","unstructured":"A. Howard, Menglong Zhu, Bo Chen, D. Kalenichenko, Weijun Wang, T. Weyand, M. Andreetto, and H. Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3185663"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Jizhou Huang Haifeng Wang Miao Fan An Zhuo and Ying Li. 2020 a. Personalized Prefix Embedding for POI Auto-Completion in the Search Engine of Baidu Maps. In KDD. 2677--2685.","DOI":"10.1145\/3394486.3403318"},{"key":"e_1_3_2_2_12_1","volume-title":"HGAMN: Heterogeneous Graph Attention Matching Network for Multilingual POI Retrieval at Baidu Maps. In KDD. 3032--3040.","author":"Huang Jizhou","year":"2021","unstructured":"Jizhou Huang, Haifeng Wang, Yibo Sun, Miao Fan, Zhengjie Huang, Chunyuan Yuan, and Yawen Li. 2021. HGAMN: Heterogeneous Graph Attention Matching Network for Multilingual POI Retrieval at Baidu Maps. In KDD. 3032--3040."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Jizhou Huang Haifeng Wang Yibo Sun Yunsheng Shi Zhengjie Huang An Zhuo and Shikun Feng. 2022. ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps. In KDD .","DOI":"10.1145\/3534678.3539021"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3396501"},{"key":"e_1_3_2_2_15_1","unstructured":"Bret Kinsella and Ava Mutchler. 2019. In-Car Voice Assistant Consumer Adoption Report."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"David R Large Gary Burnett Ben Anyasodo and Lee Skrypchuk. 2016. Assessing cognitive demand during natural language interactions with a digital driving assistant. In AutomotiveUI. 67--74.","DOI":"10.1145\/3003715.3005408"},{"key":"e_1_3_2_2_17_1","volume-title":"distraction, and cognitive control under load. Current directions in psychological science","author":"Lavie Nilli","year":"2010","unstructured":"Nilli Lavie. 2010. Attention, distraction, and cognitive control under load. Current directions in psychological science, Vol. 19, 3 (2010), 143--148."},{"key":"e_1_3_2_2_18_1","unstructured":"Tsung-Yi Lin Priya Goyal Ross Girshick Kaiming He and Piotr Doll\u00e1r. 2017b. Focal loss for dense object detection. In ICCV. 2980--2988."},{"key":"e_1_3_2_2_19_1","unstructured":"Zhouhan Lin Minwei Feng C. N. Santos Mo Yu Bing Xiang Bowen Zhou and Y. Bengio. 2017a. A structured self-attentive sentence embedding. In ICLR ."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"David McClosky Eugene Charniak and Mark Johnson. 2006. Effective self-training for parsing. In NAACL. 152--159.","DOI":"10.3115\/1220835.1220855"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Bastian Pfleging Stefan Schneegass and Albrecht Schmidt. 2012. Multimodal interaction in the car: combining speech and gestures on the steering wheel. In AutomotiveUI. 155--162.","DOI":"10.1145\/2390256.2390282"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Andreas Riener Myounghoon Jeon Ignacio Alvarez and Anna K Frison. 2017. Driver in the loop: Best practices in automotive sensing and feedback mechanisms. In AutomotiveUI. 295--323.","DOI":"10.1007\/978-3-319-49448-7_11"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Florian Roider Sonja Rumelin Bastian Pfleging and Tom Gross. 2017. The effects of situational demands on gaze speech and gesture input in the vehicle. In AutomotiveUI. 94--102.","DOI":"10.1145\/3122986.3122999"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481924"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Yu Sun Shuohuan Wang Yukun Li Shikun Feng Hao Tian Hua Wu and Haifeng Wang. 2020. Ernie 2.0: A continual pre-training framework for language understanding. In AAAI. 8968--8975.","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Amrita S Tulshan and Sudhir Namdeorao Dhage. 2018. Survey on virtual assistant: Google assistant siri cortana alexa. In SIRS. 190--201.","DOI":"10.1007\/978-981-13-5758-9_17"},{"key":"e_1_3_2_2_28_1","volume-title":"Spoken language understanding: Systems for extracting semantic information from speech","author":"Tur Gokhan","unstructured":"Gokhan Tur and Renato De Mori. 2011. Spoken language understanding: Systems for extracting semantic information from speech .John Wiley & Sons."},{"key":"e_1_3_2_2_29_1","volume-title":"Demands on driver resources associated with introducing advanced technology into the vehicle. TR_C","author":"Wierwille Walter W","year":"1993","unstructured":"Walter W Wierwille. 1993. Demands on driver resources associated with introducing advanced technology into the vehicle. TR_C, Vol. 1, 2 (1993), 133--142."},{"key":"e_1_3_2_2_30_1","unstructured":"Jinhua Xiong Qiao Zhang Shuiyuan Zhang et al. 2015. HANSpeller: a unified framework for Chinese spelling correction. In IJCLCLP. 1--22."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Baoshi Yan Fuliang Weng Zhe Feng Florin Ratiu et al. 2007. A conversational in-car dialog system. In NAACL. 23--24.","DOI":"10.3115\/1614164.1614176"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Zhao Yan Nan Duan Peng Chen Ming Zhou et al. 2017. Building Task-Oriented Dialogue Systems for Online Shopping. In AAAI. 4618--4625.","DOI":"10.1609\/aaai.v31i1.11182"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Yi Yang and Arzoo Katiyar. 2020. Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning. In EMNLP. 6365--6375.","DOI":"10.18653\/v1\/2020.emnlp-main.516"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Ruiqing Zhang Chao Pang Chuanqiang Zhang Shuohuan Wang Zhongjun He Yu Sun Hua Wu and Haifeng Wang. 2021. Correcting Chinese spelling errors with phonetic pre-training. In Findings of ACL. 2250--2261.","DOI":"10.18653\/v1\/2021.findings-acl.198"}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539030","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:50Z","timestamp":1750183790000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":33,"alternative-id":["10.1145\/3534678.3539030","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539030","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}