{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:36:44Z","timestamp":1743133004509,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819991181"},{"type":"electronic","value":"9789819991198"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-9119-8_7","type":"book-chapter","created":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T13:03:04Z","timestamp":1706878984000},"page":"68-80","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TST: Time-Sparse Transducer for\u00a0Automatic Speech Recognition"],"prefix":"10.1007","author":[{"given":"Xiaohui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mangui","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengkun","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,3]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"7_CR2","unstructured":"Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: International Conference on Machine Learning, pp. 1764\u20131772. PMLR (2014)"},{"key":"7_CR3","unstructured":"Amodei, D., et al.: Deep speech 2: end-to-end speech recognition in English and mandarin. In: International Conference on Machine Learning, pp. 173\u2013182. PMLR (2016)"},{"key":"7_CR4","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"7_CR5","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Dong, L., Xu, S., Xu, B.: Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5884\u20135888. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Kim, S., Hori, T., Watanabe, S.: Joint ctc-attention based end-to-end speech recognition using multi-task learning. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4835\u20134839. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Graves, A.: Sequence transduction with recurrent neural networks. arXiv preprint arXiv:1211.3711 (2012)","DOI":"10.1007\/978-3-642-24797-2"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.r., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6645\u20136649. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Rao, K., Sak, H., Prabhavalkar, R.: Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer. In: 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 193\u2013199. IEEE (2017)","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"7_CR11","unstructured":"He, Y., et al.: Streaming end-to-end speech recognition for mobile devices. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6381\u20136385. IEEE (2019)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Han, W., et al.: Contextnet: improving convolutional neural networks for automatic speech recognition with global context. ArXiv abs\/2005.03191 (2020)","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"7_CR13","doi-asserted-by":"publisher","unstructured":"Zhang, Q., et al.: Transformer transducer: A streamable speech recognition model with transformer encoders and rnn-t loss. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7829\u20137833 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053896","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Kannan, A., et al.: Large-scale multilingual speech recognition with a streaming end-to-end model. arXiv preprint arXiv:1909.05330 (2019)","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"7_CR15","doi-asserted-by":"publisher","unstructured":"Variani, E., Rybach, D., Allauzen, C., Riley, M.: Hybrid autoregressive transducer (hat). In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6139\u20136143 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053600","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Zhao, R., Hu, H., Gong, Y.: Improving RNN transducer modeling for end-to-end speech recognition. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 114\u2013121. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"7_CR17","doi-asserted-by":"publisher","unstructured":"Venkatesh, G., et al.: Memory-efficient speech recognition on smart devices. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8368\u20138372 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414502","DOI":"10.1109\/ICASSP39728.2021.9414502"},{"key":"7_CR18","doi-asserted-by":"publisher","unstructured":"Han, Y., Zhang, C., Li, X., Liu, Y., Wu, X.: Query-based composition for large-scale language model in lvcsr. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4898\u20134902 (2014). https:\/\/doi.org\/10.1109\/ICASSP.2014.6854533","DOI":"10.1109\/ICASSP.2014.6854533"},{"key":"7_CR19","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Sun, S., Ma, L.: Tiny transducer: a highly-efficient speech recognition model on edge devices. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6024\u20136028 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9413854","DOI":"10.1109\/ICASSP39728.2021.9413854"},{"key":"7_CR20","doi-asserted-by":"publisher","unstructured":"Chen, X., Wu, Y., Wang, Z., Liu, S., Li, J.: Developing real-time streaming transformer transducer for speech recognition on large-scale dataset. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 5904\u20135908 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9413535","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"7_CR21","doi-asserted-by":"publisher","unstructured":"Kim, C., et al.: A review of on-device fully neural end-to-end automatic speech recognition algorithms. In: 2020 54th Asilomar Conference on Signals, Systems, and Computers, pp. 277\u2013283 (2020). https:\/\/doi.org\/10.1109\/IEEECONF51394.2020.9443456","DOI":"10.1109\/IEEECONF51394.2020.9443456"},{"key":"7_CR22","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1109\/LSP.2022.3152128","volume":"29","author":"Z Tian","year":"2022","unstructured":"Tian, Z., Yi, J., Tao, J., Zhang, S., Wen, Z.: Hybrid autoregressive and non-autoregressive transformer models for speech recognition. IEEE Signal Process. Lett. 29, 762\u2013766 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"7_CR23","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.neucom.2018.11.066","volume":"331","author":"J Ostmeyer","year":"2019","unstructured":"Ostmeyer, J., Cowell, L.: Machine learning on sequential data using a recurrent weighted average. Neurocomputing 331, 281\u2013288 (2019)","journal-title":"Neurocomputing"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Bu, H., Du, J., Na, X., Wu, B., Zheng, H.: Aishell-1: an open-source mandarin speech corpus and a speech recognition baseline. In: 2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment (O-COCOSDA), pp. 1\u20135. IEEE (2017)","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Moritz, N., Hori, T., Le, J.: Streaming automatic speech recognition with the transformer model. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6074\u20136078. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Tian, Z., Yi, J., Tao, J., Bai, Y., Zhang, S., Wen, Z.: Spike-triggered non-autoregressive transformer for end-to-end speech recognition. arXiv preprint arXiv:2005.07903 (2020)","DOI":"10.21437\/Interspeech.2020-2086"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Ghodsi, M., Liu, X., Apfel, J., Cabrera, R., Weinstein, E.: Rnn-transducer with stateless prediction network. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7049\u20137053. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054419"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-9119-8_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T13:03:50Z","timestamp":1706879030000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-9119-8_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819991181","9789819991198"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-9119-8_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fuzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.cn\/#\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"376","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"101","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"16","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.9","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}