{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:05:12Z","timestamp":1784138712911,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Ant Group","award":["1"],"award-info":[{"award-number":["1"]}]},{"name":"The University of Tokyo","award":["2"],"award-info":[{"award-number":["2"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808600","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3276-3283","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4058-5123","authenticated-orcid":false,"given":"Yuejie","family":"Li","sequence":"first","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4527-9292","authenticated-orcid":false,"given":"Ke","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4456-6008","authenticated-orcid":false,"given":"Yueying","family":"Hua","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7311-2918","authenticated-orcid":false,"given":"Bolin","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5561-6635","authenticated-orcid":false,"given":"Jianhao","family":"Nie","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0775-9549","authenticated-orcid":false,"given":"Yueping","family":"He","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1924-9311","authenticated-orcid":false,"given":"Caixin","family":"Kang","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Funaudiollm: Voice understanding and generation foundation models for natural interaction between humans and llms. arXiv preprint arXiv:2407.04051","author":"An Keyu","year":"2024","unstructured":"Keyu An, Qian Chen, Chong Deng, Zhihao Du, Changfeng Gao, Zhifu Gao, Yue Gu, Ting He, Hangrui Hu, Kai Hu, et al., 2024. Funaudiollm: Voice understanding and generation foundation models for natural interaction between humans and llms. arXiv preprint arXiv:2407.04051 (2024)."},{"key":"e_1_3_2_1_2_1","unstructured":"Keyu An Yanni Chen Zhigao Chen Chong Deng Zhihao Du Changfeng Gao Zhifu Gao Bo Gong Xiangang Li Yabin Li et al. 2025. Fun-ASR Technical Report. arXiv preprint arXiv:2509.12508 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268 [cs.CL] https:\/\/arxiv.org\/abs\/1611.09268","author":"Bajaj Payal","year":"2018","unstructured":"Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268 [cs.CL] https:\/\/arxiv.org\/abs\/1611.09268"},{"key":"e_1_3_2_1_4_1","volume-title":"2015 IEEE workshop on automatic speech recognition and understanding (ASRU). IEEE, 504-511","author":"Barker Jon","year":"2015","unstructured":"Jon Barker, Ricard Marxer, Emmanuel Vincent, and Shinji Watanabe. 2015. The third 'CHiME'speech separation and recognition challenge: Dataset, task and baselines. In 2015 IEEE workshop on automatic speech recognition and understanding (ASRU). IEEE, 504-511."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jon Barker Shinji Watanabe Emmanuel Vincent and Jan Trmal. 2018. The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset task and baselines. arXiv:1803.10609 [cs.SD] https:\/\/arxiv.org\/abs\/1803.10609","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"e_1_3_2_1_6_1","volume-title":"Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216","author":"Chen Jianlv","year":"2024","unstructured":"Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216, Vol. 4, 5 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191828"},{"key":"e_1_3_2_1_8_1","unstructured":"Zhihao Du Changfeng Gao Yuxuan Wang Fan Yu Tianyu Zhao Hao Wang Xiang Lv Hui Wang Chongjia Ni Xian Shi Keyu An Guanrou Yang Yabin Li Yanni Chen Zhifu Gao Qian Chen Yue Gu Mengzhe Chen Yafeng Chen Shiliang Zhang Wen Wang and Jieping Ye. 2025. CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training. arXiv:2505.17589 [cs.SD] https:\/\/arxiv.org\/abs\/2505.17589"},{"key":"e_1_3_2_1_9_1","volume-title":"Mahmoud Al Ismail, and Huaming Wang","author":"Elizalde Benjamin","year":"2022","unstructured":"Benjamin Elizalde, Soham Deshmukh, Mahmoud Al Ismail, and Huaming Wang. 2022. CLAP: Learning Audio Concepts From Natural Language Supervision. arXiv:2206.04769 [cs.SD] https:\/\/arxiv.org\/abs\/2206.04769"},{"key":"e_1_3_2_1_10_1","volume-title":"Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to-end speech recognition. arXiv preprint arXiv:2206.08317","author":"Gao Zhifu","year":"2022","unstructured":"Zhifu Gao, Shiliang Zhang, Ian McLoughlin, and Zhijie Yan. 2022. Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to-end speech recognition. arXiv preprint arXiv:2206.08317 (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Heigold Georg","year":"2025","unstructured":"Georg Heigold, Ehsan Variani, Tom Bagby, Cyril Allauzen, Ji Ma, Shankar Kumar, and Michael Riley. 2025. Massive Sound Embedding Benchmark (MSEB). In The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_12_1","volume-title":"Sangkwon Park, Jiheum Yeom, Nohil Park, Sangwon Yu, and Sungroh Yoon.","author":"Kim Heeseung","year":"2025","unstructured":"Heeseung Kim, Che Hyun Lee, Sangkwon Park, Jiheum Yeom, Nohil Park, Sangwon Yu, and Sungroh Yoon. 2025. Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models. arXiv:2502.19759 [cs.SD] https:\/\/arxiv.org\/abs\/2502.19759"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438543"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448210"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30671-1_30"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531736"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888900"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_1_21_1","volume-title":"Specaugment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779","author":"Park Daniel S","year":"2019","unstructured":"Daniel S Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D Cubuk, and Quoc V Le. 2019. Specaugment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019)."},{"key":"e_1_3_2_1_22_1","volume-title":"DuReadertextunderscore retrieval: A Large-Scale Chinese Benchmark for Passage Retrieval from Web Search Engine. arXiv preprint arXiv:2203.10232","author":"Qiu Yifu","year":"2022","unstructured":"Yifu Qiu, Hongyu Li, Yingqi Qu, Ying Chen, Qiaoqiao She, Jing Liu, Hua Wu, and Haifeng Wang. 2022. DuReadertextunderscore retrieval: A Large-Scale Chinese Benchmark for Passage Retrieval from Web Search Engine. arXiv preprint arXiv:2203.10232 (2022)."},{"key":"e_1_3_2_1_23_1","volume-title":"Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever.","author":"Radford Alec","year":"2022","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2022. Robust Speech Recognition via Large-Scale Weak Supervision. arXiv:2212.04356 [eess.AS] https:\/\/arxiv.org\/abs\/2212.04356"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Stephen Robertson Hugo Zaragoza et al. 2009. The probabilistic relevance framework: BM25 and beyond. Foundations and trends\u00ae in information retrieval Vol. 3 4 (2009) 333-389.","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_25_1","volume-title":"Mikko A. Heikkila, Bhiksha Raj, and Nicolas Kourtellis.","author":"Shah Muhammad A.","year":"2024","unstructured":"Muhammad A. Shah, David Solans Noguero, Mikko A. Heikkila, Bhiksha Raj, and Nicolas Kourtellis. 2024. Speech Robust Bench: A Robustness Benchmark For Speech Recognition. arXiv:2403.07937 [eess.AS] https:\/\/arxiv.org\/abs\/2403.07937"},{"key":"e_1_3_2_1_26_1","unstructured":"Xian Shi Xiong Wang Zhifang Guo Yongqi Wang Pei Zhang Xinyu Zhang Zishan Guo Hongkun Hao Yu Xi Baosong Yang et al. 2026. Qwen3-ASR Technical Report. arXiv preprint arXiv:2601.21337 (2026)."},{"key":"e_1_3_2_1_27_1","volume-title":"AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines. ArXiv","author":"Shi Yao","year":"2020","unstructured":"Yao Shi, Hui Bu, Xin Xu, Shaojing Zhang, and Ming Li. 2020. AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines. ArXiv, Vol. abs\/2010.11567 (2020). https:\/\/api.semanticscholar.org\/CorpusID:225039887"},{"key":"e_1_3_2_1_28_1","volume-title":"A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering. arXiv preprint arXiv:2409.13483","author":"Sidiropoulos Georgios","year":"2024","unstructured":"Georgios Sidiropoulos and Evangelos Kanoulas. 2024. A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering. arXiv preprint arXiv:2409.13483 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557662"},{"key":"e_1_3_2_1_30_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of Meetings on Acoustics","volume":"19","author":"Thiemann Joachim","year":"2013","unstructured":"Joachim Thiemann, Nobutaka Ito, and Emmanuel Vincent. 2013. The diverse environments multi-channel acoustic noise database (demand): A database of multichannel environmental noise recordings. In Proceedings of Meetings on Acoustics, Vol. 19. Acoustical Society of America, 035081."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 3335-3338","author":"Gysel Christophe Van","year":"2023","unstructured":"Christophe Van Gysel. 2023. Modeling spoken information queries for virtual assistants: Open problems, challenges and opportunities. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 3335-3338."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"e_1_3_2_1_34_1","volume-title":"Sara Smoot, Iftekhar Naim, Joe Zou, Feiyang Chen, et al.","author":"Vera Henrique Schechter","year":"2025","unstructured":"Henrique Schechter Vera, Sahil Dua, Biao Zhang, Daniel Salz, Ryan Mullins, Sindhu Raghuram Panyam, Sara Smoot, Iftekhar Naim, Joe Zou, Feiyang Chen, et al., 2025. Embeddinggemma: Powerful and lightweight text representations. arXiv preprint arXiv:2509.20354 (2025)."},{"key":"e_1_3_2_1_35_1","volume-title":"VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing. arXiv preprint arXiv:2509.22651","author":"Wang Ke","year":"2025","unstructured":"Ke Wang, Houxing Ren, Zimu Lu, Mingjie Zhan, and Hongsheng Li. 2025. VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing. arXiv preprint arXiv:2509.22651 (2025)."},{"key":"e_1_3_2_1_36_1","volume-title":"Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672","author":"Wang Liang","year":"2024","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024. Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in neural information processing systems","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in neural information processing systems, Vol. 33 (2020), 5776-5788."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591874"},{"key":"e_1_3_2_1_41_1","unstructured":"Mengyao Xu Wenfei Zhou Yauhen Babakhin Gabriel Moreira Ronay Ak Radek Osmulski Bo Liu Even Oldridge and Benedikt Schifferer. 2025. Omni-Embed-Nemotron: A Unified Multimodal Retrieval Model for Text Image Audio and Video. arXiv:2510.03458 [cs.CL] https:\/\/arxiv.org\/abs\/2510.03458"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Heiga Zen Viet Dang Robert A. J. Clark Yu Zhang Ron J. Weiss Ye Jia Z. Chen and Yonghui Wu. 2019. LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech. In Interspeech. https:\/\/api.semanticscholar.org\/CorpusID:102352475","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"e_1_3_2_1_44_1","unstructured":"Aohan Zeng Xin Lv Qinkai Zheng Zhenyu Hou Bin Chen Chengxing Xie Cunxiang Wang Da Yin Hao Zeng Jiajie Zhang et al. 2025. Glm-4.5: Agentic reasoning and coding (arc) foundation models. arXiv preprint arXiv:2508.06471 (2025)."},{"key":"e_1_3_2_1_45_1","volume-title":"Jasper and stella: distillation of sota embedding models. arXiv preprint arXiv:2412.19048","author":"Zhang Dun","year":"2024","unstructured":"Dun Zhang, Jiacheng Li, Ziyang Zeng, and Fulong Wang. 2024. Jasper and stella: distillation of sota embedding models. arXiv preprint arXiv:2412.19048 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176","author":"Zhang Yanzhao","year":"2025","unstructured":"Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, et al., 2025. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176 (2025)."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:18:46Z","timestamp":1784135926000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808600"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":46,"alternative-id":["10.1145\/3805712.3808600","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808600","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}