{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T17:52:31Z","timestamp":1722448351821},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T00:00:00Z","timestamp":1630108800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T00:00:00Z","timestamp":1630108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10772-021-09885-1","type":"journal-article","created":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T08:02:46Z","timestamp":1630137766000},"page":"135-146","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploiting variable length segments with coarticulation effect in online speech recognition based on deep bidirectional recurrent neural network and context-sensitive segment"],"prefix":"10.1007","volume":"25","author":[{"given":"Song-Il","family":"Mun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chol-Jin","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hye-Song","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,28]]},"reference":[{"key":"9885_CR1","unstructured":"Amodei, R., Anubhai, Battenberg, E., Case, C., Casper, J., Catanzaro, B., et al. (2016). Deep speech 2: End-to-end speech recognition in English and Mandarin. Proceedings of the International Conference on Machine Learning (pp. 173\u2013182)."},{"key":"9885_CR2","unstructured":"Ba, L., Kiros, J., & Hinton, G. (2016). Layer normalization. CoRR, vol. abs\/1607.06450. http:\/\/arxiv.org\/abs\/1607.06450."},{"key":"9885_CR3","doi-asserted-by":"crossref","unstructured":"Bahdanau, D., Chorowski, J., Serdyuk, D., Brakel, P., & Bengio, Y. (2016). End-to-end attention-based large vocabulary speech recognition. ICASSP. IEEE (pp. 4945\u20134949).","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"9885_CR4","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., & Vinyals, O. (2016). Listen, attend and spell: A neural network for large vocabulary conversational speech recognition. ICASSP. IEEE (pp. 4960\u20134964).","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"9885_CR5","doi-asserted-by":"crossref","unstructured":"Chen, K., Yan, Z., & Huo, Q. (2015). Training deep bidirectional LSTM acoustic model for LVCSR by a context-sensitive-chunk BPTT Approach. Interspeech (pp. 3600\u20133604).","DOI":"10.21437\/Interspeech.2015-714"},{"key":"9885_CR6","doi-asserted-by":"crossref","unstructured":"Cho, K. et al. (2014). Learning phrase representations using rnn encoder-decoder for statistical machine translation. http:\/\/arxiv.org\/abs\/1406.1078.","DOI":"10.3115\/v1\/D14-1179"},{"key":"9885_CR7","unstructured":"Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K., & Bengio, Y. (2015). Attention-based models for speech recognition. In Advances in Neural Information Processing Systems (pp. 577\u2013585)."},{"key":"9885_CR8","doi-asserted-by":"crossref","unstructured":"Graves A., Fernandez, S., Gomez, F., and Schmidhuber, J. (2006). Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. Proceedings of the International Conference on Machine learning. ACM (pp. 369\u2013376).","DOI":"10.1145\/1143844.1143891"},{"key":"9885_CR9","doi-asserted-by":"crossref","unstructured":"Graves, A., Fernandez, S., & Schmidhuber, J. (2005). Bidirectional LSTM networks for improved phoneme classification and recognition. Proceedings of International Conference on Artificial Neural Networks (pp. 799\u2013804).","DOI":"10.1007\/11550907_126"},{"key":"9885_CR10","unstructured":"Graves, A., & Jaitly, N. (2014). Towards end-to-end speech recognition with recurrent neural networks. Proceedings of the International Conference on Machine Learning (pp. 1764\u20131772)."},{"key":"9885_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. ICASSP. IEEE (pp. 6645\u20136649).","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"9885_CR12","doi-asserted-by":"crossref","unstructured":"Hadian, H., Sameti, H., Povey, D., & Khudanpur, S. (2018). End-to-end speech recognition using lattice-free mmi. Interspeech (pp. 12\u201316).","DOI":"10.21437\/Interspeech.2018-1423"},{"issue":"6","key":"9885_CR13","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., et al. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82\u201397.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9885_CR14","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning (pp. 448\u2013456)."},{"key":"9885_CR15","doi-asserted-by":"crossref","unstructured":"Karita S., N., Soplin, Watanabe, S., Delcroix, M., Ogawa, A., & Nakatani, T. (2019). Improving Transformer-Based End-to-End Speech Recognition with Connectionist Temporal Classification and Language Model Integration. Interspeech (pp. 1408\u20131412).","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"9885_CR16","doi-asserted-by":"crossref","unstructured":"Li, X. & Wu, X., (2015). Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition. ICASSP. IEEE (pp. 4520\u20134524).","DOI":"10.1109\/ICASSP.2015.7178826"},{"key":"9885_CR17","doi-asserted-by":"crossref","unstructured":"Maas, A., Xie, Z., Jurafsky, D., & Ng, A. (2015). Lexicon-free conversational speech recognition with neural networks. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.","DOI":"10.3115\/v1\/N15-1038"},{"key":"9885_CR18","doi-asserted-by":"crossref","unstructured":"Miao, Y., Gowayyed, M., & Metze, F. (2015). Eesen: End-to-end speech recognition using deep RNN models and WFST-based decoding. Proceedings of Automatic Speech Recognition and Understanding (ASRU) (pp. 167\u2013174).","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"9885_CR19","doi-asserted-by":"crossref","unstructured":"Miao, Y., Gowayyed, M., Na, X., Ko, T., Metze, F., & Waibel, A. (2016). An empirical exploration of ctc acoustic models. ICASSP. IEEE (pp. 2623\u20132627).","DOI":"10.1109\/ICASSP.2016.7472152"},{"issue":"1","key":"9885_CR20","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1006\/csla.2001.0184","volume":"16","author":"M Mohri","year":"2002","unstructured":"Mohri, M., Pereira, F., & Riley, M. (2002). Weighted finite-state transducers in speech recognition. Computer Speech & Language, 16(1), 69\u201388.","journal-title":"Computer Speech & Language"},{"key":"9885_CR21","doi-asserted-by":"crossref","unstructured":"Morgan N., & Bourlard, H. (1990). Continuous speech recognition using multilayer perceptrons with hidden markov models. ICASSP. IEEE.","DOI":"10.1109\/ICASSP.1991.150275"},{"key":"9885_CR22","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. Interspeech (pp. 3214\u20133218).","DOI":"10.21437\/Interspeech.2015-647"},{"issue":"3","key":"9885_CR23","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1109\/LSP.2017.2723507","volume":"25","author":"V Peddinti","year":"2018","unstructured":"Peddinti, V., Wang, Y., Povey, D., & Khudanpur, S. (2018). Low latency acoustic modeling using temporal convolution and lstms. IEEE Signal Processing Letters, 25(3), 373\u2013377.","journal-title":"IEEE Signal Processing Letters"},{"key":"9885_CR24","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., et al. (2011). The Kaldi speech recognition toolkit. Proceedings of Automatic Speech Recognition and Understanding (ASRU) (pp. 1\u20134)."},{"key":"9885_CR25","doi-asserted-by":"crossref","unstructured":"Povey, D., Peddinti, V., Galvez, D., Ghahrmani, P., Manohar, V., Na, X., Wang, Y., & Khudanpur, S. (2016). Purely sequence-trained neural networks for asr based on lattice-free MMI. Interspeech (pp. 2751\u20132755).","DOI":"10.21437\/Interspeech.2016-595"},{"key":"9885_CR26","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., & Beaufays, F. (2014). Long short-term memory recurrent neural network architectures for large scale acoustic modeling. Interspeech (pp. 338\u2013342).","DOI":"10.21437\/Interspeech.2014-80"},{"key":"9885_CR27","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Rao, K., & Beaufays, F. (2015). Fast and accurate recurrent neural network acoustic models for speech recognition. Interspeech (pp. 1468\u20131472).","DOI":"10.21437\/Interspeech.2015-350"},{"key":"9885_CR28","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Rao, K., Irsoy, O., Graves, A., Beaufays, F., & J. Schalkwyk (2015). Learning acoustic frame labeling for speech recognition with recurrent neural networks. ICASSP. IEEE (pp. 4280\u20134284).","DOI":"10.1109\/ICASSP.2015.7178778"},{"issue":"11","key":"9885_CR29","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., & Paliwal, K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673\u20132681.","journal-title":"IEEE Transactions on Signal Processing"},{"key":"9885_CR30","doi-asserted-by":"crossref","unstructured":"Shi, Y., Hwang M., & Lei, X. (2019). End-to-end speech recognition using a high rank LSTM-CTC based model. ICASSP. IEEE (pp. 7080\u20137084)","DOI":"10.1109\/ICASSP.2019.8683297"},{"key":"9885_CR31","unstructured":"Sutskever, I., Martens, J., Dahl, G., & Hinton, G. (2013). On the Importance of Momentum and Initialization in Deep Learning. Proceedings of the International Conference on Machine Learning."},{"key":"9885_CR32","doi-asserted-by":"crossref","unstructured":"Tian, Z., Yi, J., Tao, J., Bai, Y., & Wen, Z. 2019. Self-Attention Transducers for End-to-End Speech Recognition. Interspeech (pp. 4395\u20134399).","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"9885_CR33","doi-asserted-by":"crossref","unstructured":"Xue, S. & Yan, Z. (2017). Improving latency-controlled BLSTM acoustic models for online speech recognition. ICASSP. IEEE.","DOI":"10.1109\/ICASSP.2017.7953176"},{"key":"9885_CR34","unstructured":"Yu, D., & Deng, L. (2014). Automatic speech recognition: A deep learning approach. Springer."},{"key":"9885_CR35","doi-asserted-by":"crossref","unstructured":"Zeyer, A., Schluter, R., & Ney, H. (2016). Towards online-recognition with deep bidirectional LSTM acoustic models. Interspeech (pp. 3424\u20133428).","DOI":"10.21437\/Interspeech.2016-759"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09885-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09885-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09885-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T18:38:28Z","timestamp":1647369508000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09885-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,28]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["9885"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09885-1","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,28]]},"assertion":[{"value":"17 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There are no our items corresponding to the guideline.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}