{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:38:10Z","timestamp":1740148690668,"version":"3.37.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2019,10,16]],"date-time":"2019-10-16T00:00:00Z","timestamp":1571184000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,10,16]],"date-time":"2019-10-16T00:00:00Z","timestamp":1571184000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1007\/s11265-019-01482-5","type":"journal-article","created":{"date-parts":[[2019,10,16]],"date-time":"2019-10-16T18:57:52Z","timestamp":1571252272000},"page":"839-851","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Public Chinese Dataset for Language Model Adaptation"],"prefix":"10.1007","volume":"92","author":[{"given":"Ye","family":"Bai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-4618","authenticated-orcid":false,"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cunhang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,16]]},"reference":[{"key":"1482_CR1","unstructured":"Jurafsky, D. (2000). Speech & language processing. Pearson Education India."},{"issue":"8","key":"1482_CR2","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1109\/5.880083","volume":"88","author":"R Rosenfeld","year":"2000","unstructured":"Rosenfeld, R. (2000). Two decades of statistical language modeling: Where do we go from here? Proceedings of the IEEE, 88(8), 1270\u20131278.","journal-title":"Proceedings of the IEEE"},{"issue":"1","key":"1482_CR3","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.specom.2003.08.002","volume":"42","author":"JR Bellegarda","year":"2004","unstructured":"Bellegarda, J. R. (2004). Statistical language model adaptation: review and perspectives. Speech Communication, 42(1), 93\u2013108.","journal-title":"Speech Communication"},{"issue":"6","key":"1482_CR4","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1109\/34.56193","volume":"12","author":"R Kuhn","year":"1990","unstructured":"Kuhn, R., & De Mori, R. (1990). A cache-based natural language model for speech recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(6), 570\u2013583.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1482_CR5","unstructured":"Jelinek, F., Merialdo, B., Roukos, S., & Strauss, M. (1991). A dynamic language model for speech recognition. In Speech and Natural Language: Proceedings of a Workshop Held at Pacific Grove, California, February 19-22, 1991."},{"key":"1482_CR6","doi-asserted-by":"crossref","unstructured":"Rao, P. S., Dharanipragada, S., & Roukos, S. (1997). MDI adaptation of language models across corpora. In Fifth European Conference on Speech Communication and Technology.","DOI":"10.21437\/Eurospeech.1997-525"},{"key":"1482_CR7","doi-asserted-by":"crossref","unstructured":"Xu, W., & Rudnicky, A. (2000). Can artificial neural networks learn language models?. In Sixth International Conference on Spoken Language Processing.","DOI":"10.21437\/ICSLP.2000-50"},{"issue":"Feb","key":"1482_CR8","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio, Y., Ducharme, R., Vincent, P., & Jauvin, C. (2003). A neural probabilistic language model. Journal of Machine Learning Research, 3(Feb), 1137\u20131155.","journal-title":"Journal of Machine Learning Research"},{"key":"1482_CR9","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., \u010cernock\u00fd, J., & Khudanpur, S. (2010). Recurrent neural network based language model. In Eleventh Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2010-343"},{"key":"1482_CR10","doi-asserted-by":"crossref","unstructured":"Takase, S., Suzuki, J., & Nagata, M. (2018). Direct Output Connection for a High-Rank Language Model. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (pp. 4599-4609).","DOI":"10.18653\/v1\/D18-1489"},{"key":"1482_CR11","unstructured":"Yang, Z., Dai, Z., Salakhutdinov, R., & Cohen, W. W. (2017). Breaking the softmax bottleneck: A high-rank RNN language model. arXiv preprint arXiv:1711.03953."},{"key":"1482_CR12","doi-asserted-by":"crossref","unstructured":"Chen, X., Tan, T., Liu, X., Lanchantin, P., Wan, M., Gales, M. J., & Woodland, P. C. (2015). Recurrent neural network language model adaptation for multi-genre broadcast speech recognition. In Sixteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2015-696"},{"key":"1482_CR13","doi-asserted-by":"crossref","unstructured":"Deena, S., Ng, R. W., Madhyashta, P., Specia, L., & Hain, T. (2017). Semi-supervised adaptation of RNNLMs by fine-tuning with domain-specific auxiliary features. In Eighteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2017-1598"},{"key":"1482_CR14","doi-asserted-by":"crossref","unstructured":"Li, K., Xu, H., Wang, Y., Povey, D., & Khudanpur, S. (2018). Recurrent neural network language model adaptation for conversational speech recognition. In Nighteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2018-1413"},{"key":"1482_CR15","unstructured":"Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805."},{"key":"1482_CR16","unstructured":"Peters, M. E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018). Deep contextualized word representations. arXiv preprint arXiv:1802.05365."},{"key":"1482_CR17","unstructured":"Melis, G., Dyer, C., & Blunsom, P. (2017). On the state of the art of evaluation in neural language models. arXiv preprint arXiv:1707.05589."},{"key":"1482_CR18","doi-asserted-by":"crossref","unstructured":"Kim, Y., Jernite, Y., Sontag, D., & Rush, A. M. (2016). Character-Aware Neural Language Models. In AAAI (pp. 2741-2749).","DOI":"10.1609\/aaai.v30i1.10362"},{"key":"1482_CR19","doi-asserted-by":"crossref","unstructured":"Chelba, C., Mikolov, T., Schuster, M., Ge, Q., Brants, T., Koehn, P., & Robinson, T. (2014). One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling. In Fifteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2014-564"},{"key":"1482_CR20","doi-asserted-by":"crossref","unstructured":"Xu, H., Li, K., Wang, Y., Wang, J., Kang, S., Chen, X., ... & Khudanpur, S. (2018, April). Neural network language modeling with letter-based features and importance sampling. In Acoustics, Speech and Signal Processing (ICASSP), 2018 IEEE International Conference on. IEEE.","DOI":"10.1109\/ICASSP.2018.8461704"},{"key":"1482_CR21","doi-asserted-by":"crossref","unstructured":"Xu, H., Chen, T., Gao, D., Wang, Y., Li, K., Goel, N., ... & Khudanpur, S. (2018). A Pruned RNNLM Lattice-Rescoring Algorithm for Automatic Speech Recognition. In Nighteenth Annual Conference of the International Speech Communication Association.","DOI":"10.1109\/ICASSP.2018.8461974"},{"key":"1482_CR22","doi-asserted-by":"publisher","first-page":"3348","DOI":"10.21437\/Interspeech.2018-1111","volume":"2018","author":"Y Zhang","year":"2018","unstructured":"Zhang, Y., Zhang, P., & Yan, Y. (2018). Improving Language Modeling with an Adversarial Critic for Automatic Speech Recognition. Proc. Interspeech, 2018, 3348\u20133352.","journal-title":"Proc. Interspeech"},{"key":"1482_CR23","doi-asserted-by":"crossref","unstructured":"Bell, P., Gales, M. J., Hain, T., Kilgour, J., Lanchantin, P., Liu, X., ... & Woodland, P. C. (2015). The MGB challenge: Evaluating multi-genre broadcast media recognition. In Automatic Speech Recognition and Understanding (ASRU), 2015 IEEE Workshop on (pp. 687-693). IEEE.","DOI":"10.1109\/ASRU.2015.7404863"},{"key":"1482_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, H. P., Yu, H. K., Xiong, D. Y., & Liu, Q. (2003). HHMM-based Chinese lexical analyzer ICTCLAS. In Proceedings of the second SIGHAN workshop on Chinese language processing-Volume 17 (pp. 184-187). Association for Computational Linguistics.","DOI":"10.3115\/1119250.1119280"},{"key":"1482_CR25","doi-asserted-by":"crossref","unstructured":"Stolcke, A. (2002). SRILM-an extensible language modeling toolkit. In Seventh international conference on spoken language processing.","DOI":"10.21437\/ICSLP.2002-303"},{"key":"1482_CR26","doi-asserted-by":"crossref","unstructured":"Kuznetsov, V., Liao, H., Mohri, M., Riley, M., & Roark, B. (2016). Learning N-Gram Language Models from Uncertain Data. In Seventeenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2016-1093"},{"key":"1482_CR27","doi-asserted-by":"crossref","unstructured":"Bene\u0161, K., Kesiraju, S., Burget, L. (2018) i-Vectors in Language Modeling: An Efficient Way of Domain Adaptation for Feed-Forward Models. In Nighteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2018-1070"},{"key":"1482_CR28","doi-asserted-by":"crossref","unstructured":"Ma, M., Nirschl, M., Biadsy, F., & Kumar, S. (2017). Approaches for neural-network language model adaptation. In Eighteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2017-1310"},{"key":"1482_CR29","doi-asserted-by":"crossref","unstructured":"Gangireddy, S. R., Swietojanski, P., Bell, P., & Renals, S. (2016). Unsupervised Adaptation of Recurrent Neural Network Language Models. In Seventeenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2016-1342"},{"key":"1482_CR30","doi-asserted-by":"crossref","unstructured":"Andr\u00e9s-Ferrer, J., Bodenstab, N., & Vozila, P. (2018). Efficient Language Model Adaptation with Noise Contrastive Estimation and Kullback-Leibler Regularization. In Nighteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2018-1345"},{"issue":"8","key":"1482_CR31","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"key":"1482_CR32","unstructured":"Chung, J., et al. (2014) \"Empirical evaluation of gated recurrent neural networks on sequence modeling.\" arXiv preprint arXiv:1412.3555."},{"issue":"10","key":"1482_CR33","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1109\/5.58337","volume":"78","author":"PJ Werbos","year":"1990","unstructured":"Werbos, P. J. (1990). Backpropagation through time: what it does and how to do it. Proceedings of the IEEE, 78(10), 1550\u20131560.","journal-title":"Proceedings of the IEEE"},{"key":"1482_CR34","doi-asserted-by":"crossref","unstructured":"Liu, X., et al. (2014) \"Efficient lattice rescoring using recurrent neural network language models.\" 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE.","DOI":"10.1109\/ICASSP.2014.6854535"},{"key":"1482_CR35","doi-asserted-by":"crossref","unstructured":"Emami, A., and Mangu L. (2007) \"Empirical study of neural network language models for Arabic speech recognition.\" 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU). IEEE.","DOI":"10.1109\/ASRU.2007.4430100"},{"issue":"3","key":"1482_CR36","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1016\/j.csl.2006.09.003","volume":"21","author":"H Schwenk","year":"2007","unstructured":"Schwenk, H. (2007). Continuous space language models. Computer Speech & Language, 21(3), 492\u2013518.","journal-title":"Computer Speech & Language"},{"key":"1482_CR37","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., ... & Kudlur, M. (2016). Tensorflow: a system for large-scale machine learning. In OSDI (Vol. 16, pp. 265-283)."},{"key":"1482_CR38","doi-asserted-by":"crossref","unstructured":"Bu, H., Du, J., Na, X., Wu, B., & Zheng, H. (2017). 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. 1-5). IEEE.","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"1482_CR39","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., ... & Silovsky, J. (2011). The Kaldi speech recognition toolkit. In IEEE 2011 workshop on automatic speech recognition and understanding (No. EPFL-CONF-192584). IEEE Signal Processing Society."},{"key":"1482_CR40","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Povey, D., & Khudanpur, S. (2015). A time delay neural network architecture for efficient modeling of long temporal contexts. In Sixteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2015-647"},{"key":"1482_CR41","doi-asserted-by":"crossref","unstructured":"Povey, D., Peddinti, V., Galvez, D., Ghahremani, P., Manohar, V., Na, X., ... & Khudanpur, S. (2016). Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI. In Seventeenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2016-595"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-019-01482-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-019-01482-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-019-01482-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T22:58:54Z","timestamp":1664665134000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-019-01482-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,16]]},"references-count":41,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2020,8]]}},"alternative-id":["1482"],"URL":"https:\/\/doi.org\/10.1007\/s11265-019-01482-5","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"type":"print","value":"1939-8018"},{"type":"electronic","value":"1939-8115"}],"subject":[],"published":{"date-parts":[[2019,10,16]]},"assertion":[{"value":"15 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}