{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:51:15Z","timestamp":1755802275419,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":5,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"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":[[2025,3,10]]},"DOI":"10.1145\/3701551.3706130","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:30:16Z","timestamp":1740573016000},"page":"1084-1085","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Advancing Voice AI for E-commerce: Tracking ASR Model Performance at Scale"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1082-496X","authenticated-orcid":false,"given":"Dhruv","family":"Agarwal","sequence":"first","affiliation":[{"name":"Amazon, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9272-3657","authenticated-orcid":false,"given":"Nupur","family":"Neti","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9171-0746","authenticated-orcid":false,"given":"Federica","family":"Cerina","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919","author":"Chu Yunfei","year":"2023","unstructured":"Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, and Jingren Zhou. 2023. Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"e_1_3_2_1_3_1","volume-title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations. arXiv preprint arXiv:2402.01912","author":"Lyth Dan","year":"2024","unstructured":"Dan Lyth and Simon King. 2024. Natural language guidance of high-fidelity text-to-speech with synthetic annotations. arXiv preprint arXiv:2402.01912 (2024)."},{"key":"e_1_3_2_1_4_1","volume-title":"International conference on machine learning. PMLR, 28492--28518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International conference on machine learning. PMLR, 28492--28518."},{"key":"e_1_3_2_1_5_1","volume-title":"2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No. 01CH37221)","volume":"2","author":"Rix Antony W.","unstructured":"Antony W. Rix, John G. Beerends, Michael P. Hollier, and Andries P. Hekstra. 2001. Perceptual evaluation of speech quality (PESQ) - a new method for speech quality assessment of telephone networks and codecs. In 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No. 01CH37221), Vol. 2. IEEE, 749--752."}],"event":{"name":"WSDM '25: The Eighteenth ACM International Conference on Web Search and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Hannover Germany","acronym":"WSDM '25"},"container-title":["Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3706130","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701551.3706130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:12:16Z","timestamp":1755767536000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3706130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":5,"alternative-id":["10.1145\/3701551.3706130","10.1145\/3701551"],"URL":"https:\/\/doi.org\/10.1145\/3701551.3706130","relation":{},"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"2025-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}