{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:45:46Z","timestamp":1726062346180},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030367176"},{"type":"electronic","value":"9783030367183"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-36718-3_25","type":"book-chapter","created":{"date-parts":[[2019,12,10]],"date-time":"2019-12-10T03:03:52Z","timestamp":1575947032000},"page":"295-305","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Fast Convolutional Self-attention Based Speech Dereverberation Method for Robust Speech Recognition"],"prefix":"10.1007","author":[{"given":"Nan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,12,9]]},"reference":[{"key":"25_CR1","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2013","unstructured":"Xu, Y., Du, J., Dai, L.R., Lee, C.: An experimental study on speech enhancement based on deep neural networks. IEEE Signal Process. Lett. 21, 65\u201368 (2013)","journal-title":"IEEE Signal Process. Lett."},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Wang, D.: Learning spectral mapping for speech dereverberation. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4628\u20134632 (2014)","DOI":"10.1109\/ICASSP.2014.6854479"},{"issue":"14","key":"25_CR3","doi-asserted-by":"publisher","first-page":"18865","DOI":"10.1007\/s11042-018-5686-1","volume":"77","author":"Z Oo","year":"2018","unstructured":"Oo, Z., Wang, L., Phapatanaburi, K., Nakagawa, S., Iwahashi, M., Dang, J.: Phase and reverberation aware DNN for distant-talking speech enhancement. Multimed. Tools Appl. 77(14), 18865\u201318880 (2018)","journal-title":"Multimed. Tools Appl."},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Park, S.R., Lee, J.: A fully convolutional neural network for speech enhancement. In: Interspeech 2017, pp. 1993\u20131997 (2017)","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Fu, S.W., Tsao, Y., Lu, X., Kawai, H.: Raw waveform-based speech enhancement by fully convolutional networks. In: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 006\u2013012 (2017)","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Weninger, F., Watanabe, S., Tachioka, Y., Schuller, B.: Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4623\u20134627 (2014)","DOI":"10.1109\/ICASSP.2014.6854478"},{"key":"25_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","volume-title":"Latent Variable Analysis and Signal Separation","author":"F Weninger","year":"2015","unstructured":"Weninger, F., et al.: Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR. In: Vincent, E., Yeredor, A., Koldovsk\u00fd, Z., Tichavsk\u00fd, P. (eds.) LVA\/ICA 2015. LNCS, vol. 9237, pp. 91\u201399. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-22482-4_11"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Ge, M., Wang, L., Li, N., Shi, H., Dang, J., Li, X.: Environment-dependent attention-driven recurrent convolutional neural network for robust speech enhancement. In: Interspeech 2019, pp. 3153\u20133157 (2019)","DOI":"10.21437\/Interspeech.2019-1477"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Pascual, S., Bonafonte, A., Serr\u00e0, J.: SEGAN: speech enhancement generative adversarial network. In: Interspeech 2017, pp. 3642\u20133646 (2017)","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Wang, K., Zhang, J., Sun, S.: Investigating generative adversarial networks based speech dereverberation for robust speech recognition. In: Interspeech 2018, pp. 1581\u20131585 (2018)","DOI":"10.21437\/Interspeech.2018-1780"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Li, C., Wang, T., Xu, S., Xu, B.: Single-channel speech dereverberation via generative adversarial training. In: Interspeech 2018, pp. 1309\u20131313 (2018)","DOI":"10.21437\/Interspeech.2018-1234"},{"issue":"1","key":"25_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13634-015-0278-y","volume":"2015","author":"Y Ueda","year":"2015","unstructured":"Ueda, Y., Wang, L., Kai, A., Ren, B.: Environment-dependent denoising autoencoder for distant-talking speech recognition. EURASIP J. Adv. Signal Process. 2015(1), 1\u201311 (2015)","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Narayanan, A., Wang, D.: Ideal ratio mask estimation using deep neural networks for robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7092\u20137096 (2013)","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"25_CR14","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","volume":"24","author":"DS Williamson","year":"2016","unstructured":"Williamson, D.S., Wang, Y., Wang, D.: Complex ratio masking for monaural speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 24, 483\u2013492 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"25_CR15","unstructured":"Vaswani, A., Shazeer, N., Parmar, N.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Paulik, M.: Lattice-based training of bottleneck feature extraction neural networks. In: Interspeech 2013, pp. 89\u201393 (2013)","DOI":"10.21437\/Interspeech.2013-44"},{"key":"25_CR17","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.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29, 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Kinoshita, K., Delcroix, M., Yoshioka, T.: The REVERB challenge: a common evaluation framework for dereverberation and recognition of reverberant speech. In: IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (2014)","DOI":"10.1109\/WASPAA.2013.6701894"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Zhou, S., Dong, L., Xu, S., Xu, B.: Syllable-based sequence-to-sequence speech recognition with the transformer in Mandarin Chinese. In: Interspeech 2018, pp. 791\u2013795 (2018)","DOI":"10.21437\/Interspeech.2018-1107"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Chiu, C.C., Sainath, T.N., Wu, Y.: State-of-the-art speech recognition with sequence-to-sequence models. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4774\u20134778 (2018)","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"25_CR21","unstructured":"Devlin, J., Chang, M.W., Lee, K.: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"25_CR22","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"issue":"9","key":"25_CR23","doi-asserted-by":"publisher","first-page":"5093","DOI":"10.1007\/s11042-015-2849-1","volume":"75","author":"B Ren","year":"2016","unstructured":"Ren, B., Wang, L., Lu, L., Ueda, Y., Kai, A.: Combination of bottleneck feature extraction and dereverberation for distant-talking speech recognition. Multimed. Tools Appl. 75(9), 5093\u20135108 (2016)","journal-title":"Multimed. Tools Appl."},{"key":"25_CR24","unstructured":"Xu, Y., Du, J., Huang, Z.: Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement (2017)"},{"key":"25_CR25","unstructured":"Graff, D., Kong, J., Chen, K.: English gigaword. Linguist. Data Consortium Philadelphia"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Lincoln, M., McCowan, I., Vepa, J.: The multi-channel Wall Street Journal audio visual corpus (MC-WSJ-AV): specification and initial experiments. In: IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 357\u2013362 (2005)","DOI":"10.1109\/ASRU.2005.1566470"},{"key":"25_CR27","unstructured":"Povey, D., Ghoshal, A., Boulianne, G.: The Kaldi speech recognition toolkit. In: IEEE Signal Processing Society (2011)"},{"key":"25_CR28","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36718-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T22:05:32Z","timestamp":1665180332000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-36718-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030367176","9783030367183"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36718-3_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ajiips.com.au\/iconip2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}