{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:32Z","timestamp":1750219772073,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,14]],"date-time":"2023-07-14T00:00:00Z","timestamp":1689292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Fundamental Research Funds for the Central Universities","award":["2023QN1079"],"award-info":[{"award-number":["2023QN1079"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,14]]},"DOI":"10.1145\/3614008.3614062","type":"proceedings-article","created":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T18:19:52Z","timestamp":1697566792000},"page":"363-367","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated Speech Recognition System for Dispatching Call Recordings in The Underground Coal Mines"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5841-6365","authenticated-orcid":false,"given":"Guoyuan","family":"Lin","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, China and \rEngineering Research Center of Ministry of Education for Mine Digitalization, China University of Mining and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5403-9047","authenticated-orcid":false,"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[{"name":"HUAIBEI MINING GROUP, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2986-2605","authenticated-orcid":false,"given":"Jueting","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4649-9790","authenticated-orcid":false,"given":"Zemeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Jiangsu Novolion Technology Company, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4820-5366","authenticated-orcid":false,"given":"Minda","family":"Yao","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7663-278X","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3072-072X","authenticated-orcid":false,"given":"Yingchun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9040-847X","authenticated-orcid":false,"given":"Zehua","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1631-6283","authenticated-orcid":false,"given":"Hengbo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,17]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Sohn Jongseo Nam Soo Kim and Wonyong Sung. \"A statistical model-based voice activity detection.\"\u00a0IEEE signal processing letters\u00a06.1 (1999): 1-3.  Sohn Jongseo Nam Soo Kim and Wonyong Sung. \"A statistical model-based voice activity detection.\"\u00a0IEEE signal processing letters\u00a06.1 (1999): 1-3.","key":"e_1_3_2_1_1_1","DOI":"10.1109\/97.736233"},{"doi-asserted-by":"crossref","unstructured":"Gulati Anmol \"Conformer: Convolution-augmented transformer for speech recognition.\"\u00a0arXiv preprint arXiv:2005.08100\u00a0(2020).  Gulati Anmol \"Conformer: Convolution-augmented transformer for speech recognition.\"\u00a0arXiv preprint arXiv:2005.08100\u00a0(2020).","key":"e_1_3_2_1_2_1","DOI":"10.21437\/Interspeech.2020-3015"},{"doi-asserted-by":"crossref","unstructured":"Sharma Mayank \"A comprehensive empirical review of modern voice activity detection approaches for movies and TV shows.\"\u00a0Neurocomputing\u00a0(2022).  Sharma Mayank \"A comprehensive empirical review of modern voice activity detection approaches for movies and TV shows.\"\u00a0Neurocomputing\u00a0(2022).","key":"e_1_3_2_1_3_1","DOI":"10.1016\/j.neucom.2022.04.084"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1109\/TASL.2011.2125953"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1049\/el:20000192"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1016\/j.specom.2003.10.002"},{"doi-asserted-by":"crossref","unstructured":"Greff Klaus \"LSTM: A search space odyssey.\"\u00a0IEEE transactions on neural networks and learning systems\u00a028.10 (2016): 2222-2232.  Greff Klaus \"LSTM: A search space odyssey.\"\u00a0IEEE transactions on neural networks and learning systems\u00a028.10 (2016): 2222-2232.","key":"e_1_3_2_1_7_1","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"e_1_3_2_1_8_1","volume-title":"IEEE","author":"Ferroni","year":"2015","unstructured":"Ferroni , Giacomo, \"A deep neural network approach for voice activity detection in multi-room domestic scenarios.\"\u00a02015 International Joint Conference on Neural Networks (IJCNN) . IEEE , 2015 . Ferroni, Giacomo, \"A deep neural network approach for voice activity detection in multi-room domestic scenarios.\"\u00a02015 International Joint Conference on Neural Networks (IJCNN). IEEE, 2015."},{"unstructured":"K. Simonyan A. Zisserman Very deep convolutional networks for large-scale image recognition arXiv preprint arXiv:1409.1556.  K. Simonyan A. Zisserman Very deep convolutional networks for large-scale image recognition arXiv preprint arXiv:1409.1556.","key":"e_1_3_2_1_9_1"},{"key":"e_1_3_2_1_10_1","volume-title":"Automatic recognition of spoken digits. J Acoust Soc Am 24(6):637\u2013642","author":"Davis KH","year":"1952","unstructured":"Davis KH , Biddulph R , Balashek S ( 1952 ) Automatic recognition of spoken digits. J Acoust Soc Am 24(6):637\u2013642 Davis KH, Biddulph R, Balashek S (1952) Automatic recognition of spoken digits. J Acoust Soc Am 24(6):637\u2013642"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1002\/j.1538-7305.1984.tb00034.x"},{"key":"e_1_3_2_1_12_1","volume-title":"75-98","author":"Gales JF.","year":"1998","unstructured":"Gales , Mark JF. \" Maximum likelihood linear transformations for HMM-based speech recognition.\" Computer speech & language 12.2 ( 1998 ): 75-98 . Gales, Mark JF. \"Maximum likelihood linear transformations for HMM-based speech recognition.\" Computer speech & language 12.2 (1998): 75-98."},{"key":"e_1_3_2_1_13_1","volume-title":"IEEE","author":"Li","year":"2012","unstructured":"Li , Jinyu, \" Improving wideband speech recognition using mixed-bandwidth training data in CD-DNN-HMM.\" 2012 IEEE Spoken Language Technology Workshop (SLT) . IEEE , 2012 . Li, Jinyu, \"Improving wideband speech recognition using mixed-bandwidth training data in CD-DNN-HMM.\" 2012 IEEE Spoken Language Technology Workshop (SLT). IEEE, 2012."},{"key":"e_1_3_2_1_14_1","volume-title":"Acoustic-to-word LSTM model for large vocabulary speech recognition.\" arXiv preprint arXiv:1610.09975","author":"Soltau","year":"2016","unstructured":"Soltau , Hagen, Hank Liao , and Hasim Sak. \"Neural speech recognizer : Acoustic-to-word LSTM model for large vocabulary speech recognition.\" arXiv preprint arXiv:1610.09975 ( 2016 ). Soltau, Hagen, Hank Liao, and Hasim Sak. \"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition.\" arXiv preprint arXiv:1610.09975 (2016)."},{"key":"e_1_3_2_1_15_1","volume-title":"Speech and Signal Processing. IEEE","author":"Mamiya","year":"2013","unstructured":"Mamiya , Yoshitaka, \" Lightly supervised GMM VAD to use audiobook for speech synthesiser.\"\u00a02013 IEEE International Conference on Acoustics , Speech and Signal Processing. IEEE , 2013 . Mamiya, Yoshitaka, \"Lightly supervised GMM VAD to use audiobook for speech synthesiser.\"\u00a02013 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 2013."},{"key":"e_1_3_2_1_16_1","volume-title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition. ArXiv. \/abs\/2110.03370","author":"Zhang B.","year":"2021","unstructured":"Zhang , B. , Lv , H. , Guo , P. , Shao , Q. , Yang , C. , Xie , L. , Xu , X. , Bu , H. , Chen , X. , Zeng , C. , Wu , D. , & Peng , Z. ( 2021 ). WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition. ArXiv. \/abs\/2110.03370 . Zhang, B., Lv, H., Guo, P., Shao, Q., Yang, C., Xie, L., Xu, X., Bu, H., Chen, X., Zeng, C., Wu, D., & Peng, Z. (2021). WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition. ArXiv. \/abs\/2110.03370."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1016\/S0167-6393(01)00041-3"}],"event":{"acronym":"SPML 2023","name":"SPML 2023: 2023 6th International Conference on Signal Processing and Machine Learning","location":"Tianjin China"},"container-title":["2023 6th International Conference on Signal Processing and Machine Learning (SPML)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3614008.3614062","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3614008.3614062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:27Z","timestamp":1750178247000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3614008.3614062"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,14]]},"references-count":17,"alternative-id":["10.1145\/3614008.3614062","10.1145\/3614008"],"URL":"https:\/\/doi.org\/10.1145\/3614008.3614062","relation":{},"subject":[],"published":{"date-parts":[[2023,7,14]]},"assertion":[{"value":"2023-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}