{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:07:01Z","timestamp":1781586421372,"version":"3.54.5"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319646794","type":"print"},{"value":"9783319646800","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-64680-0_14","type":"book-chapter","created":{"date-parts":[[2017,10,31]],"date-time":"2017-10-31T08:37:26Z","timestamp":1509439046000},"page":"327-344","source":"Crossref","is-referenced-by-count":17,"title":["The CHiME Challenges: Robust Speech Recognition in Everyday Environments"],"prefix":"10.1007","author":[{"given":"Jon P.","family":"Barker","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ricard","family":"Marxer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Vincent","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,7,26]]},"reference":[{"issue":"7","key":"14_CR1","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TASL.2007.902460","volume":"15","author":"X. Anguera","year":"2007","unstructured":"Anguera, X., Wooters, C., Hernando, J.: Acoustic beamforming for speaker diarization of meetings. IEEE Trans. Audio Speech Lang. Process. 15(7), 2011\u20132023 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"14_CR2","unstructured":"Baby, D., Virtanen, T., Van\u00a0Hamme, H.: Coupled dictionary-based speech enhancement for CHiME-3 challenge. Technical Report KUL\/ESAT\/PSI\/1503, KU Leuven, ESAT, Leuven (2015)"},{"key":"14_CR3","unstructured":"Barfuss, H., Huemmer, C., Schwarz, A., Kellermann, W.: Robust coherence-based spectral enhancement for distant speech recognition (2015). arXiv:1509.06882"},{"issue":"3","key":"14_CR4","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1016\/j.csl.2012.10.004","volume":"27","author":"J. Barker","year":"2013","unstructured":"Barker, J., Vincent, E., Ma, N., Christensen, H., Green, P.: The PASCAL CHiME speech separation and recognition challenge. Comput. Speech Lang. 27(3), 621\u2013633 (2013)","journal-title":"Comput. Speech Lang."},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Barker, J., Marxer, R., Vincent, E., Watanabe, S.: The third \u2018CHiME\u2019 speech separation and recognition challenge: dataset, task and baselines. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp. 504\u2013511 (2015). doi:10.1109\/ASRU.2015.7404837","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Christensen, H., Barker, J., Ma, N., Green, P.: The CHiME corpus: a resource and a challenge for computational hearing in multisoure environments. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association (Interspeech 2010), Makuhari (2010)","DOI":"10.21437\/Interspeech.2010-552"},{"issue":"5","key":"14_CR7","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"M. Cooke","year":"2006","unstructured":"Cooke, M., Barker, J., Cunningham, S., Shao, X.: An audio-visual corpus for speech perception and automatic speech recognition. J. Acoust. Soc. Am. 120(5), 2421\u20132424 (2006). doi:10.1121\/1.2229005","journal-title":"J. Acoust. Soc. Am."},{"key":"14_CR8","unstructured":"Delcroix, M., Kinoshita, K., Nakatani, T., Araki, S., Ogawa, A., Hori, T., Watanabe, S., Fujimoto, M., Yoshioka, T., Oba, T., Kubo, Y., Souden, M., Hahm, S.J., Nakamura, A.: Speech recognition in the presence of highly non-stationary noise based on spatial, spectral and temporal speech\/noise modeling combined with dynamic variance adaptation. In: Proceedings of the 1st CHiME Workshop on Machine Listening in Multisource Environments, Florence, pp.\u00a012\u201317 (2011)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Du, J., Wang, Q., Tu, Y.H., Bao, X., Dai, L.R., Lee, C.H.: An information fusion approach to recognizing microphone array speech in the CHiME-3 challenge based on a deep learning framework. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp. 430\u2013435 (2015)","DOI":"10.1109\/ASRU.2015.7404827"},{"key":"14_CR10","unstructured":"El-Desoky\u00a0Mousa, A., Marchi, E., Schuller, B.: The ICSTM+TUM+UP approach to the 3rd CHiME challenge: single-channel LSTM speech enhancement with multi-channel correlation shaping dereverberation and LSTM language models (2015). arXiv:1510.00268"},{"key":"14_CR11","unstructured":"Farina, A.: Simultaneous measurement of impulse response and distortion with a swept sine technique. In: Proceedings of the 108th AES Convention, Paris (2000)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Fujita, Y., Takashima, R., Homma, T., Ikeshita, R., Kawaguchi, Y., Sumiyoshi, T., Endo, T., Togami, M.: Unified ASR system using LGM-based source separation, noise-robust feature extraction, and word hypothesis selection. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp. 416\u2013422 (2015)","DOI":"10.1109\/ASRU.2015.7404825"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Heymann, J., Drude, L., Chinaev, A., Haeb-Umbach, R.: BLSTM supported GEV beamformer front-end for the 3rd CHiME challenge. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp. 444\u2013451 (2015)","DOI":"10.1109\/ASRU.2015.7404829"},{"key":"14_CR14","unstructured":"Hirsch, H.G., Pearce, D.: The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP), vol.\u00a04, pp.\u00a029\u201332 (2000)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Hori, T., Chen, Z., Erdogan, H., Hershey, J.R., Le\u00a0Roux, J., Mitra, V., Watanabe, S.: The MERL\/SRI system for the 3rd CHiME challenge using beamforming, robust feature extraction, and advanced speech recognition. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp.\u00a0475\u2013481 (2015)","DOI":"10.1109\/ASRU.2015.7404833"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Ma, N., Marxer, R., Barker, J., Brown, G.J.: Exploiting synchrony spectra and deep neural networks for noise-robust automatic speech recognition. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp.\u00a0490\u2013495 (2015)","DOI":"10.1109\/ASRU.2015.7404835"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Moritz, N., Gerlach, S., Adiloglu, K., Anem\u00fcller, J., Kollmeier, B., Goetze, S.: A CHiME-3 challenge system: long-term acoustic features for noise robust automatic speech recognition. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp.\u00a0468\u2013474 (2015)","DOI":"10.1109\/ASRU.2015.7404832"},{"issue":"3\u20134","key":"14_CR18","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1007\/s10579-007-9054-4","volume":"41","author":"D. Mostefa","year":"2007","unstructured":"Mostefa, D., Moreau, N., Choukri, K., Potamianos, G., Chu, S.M., Tyagi, A., Casas, J.R., Turmo, J., Cristoforetti, L., Tobia, F.,, Pnevmatikakis, A., Mylonakis, V., Talantzis, F., Burger, S., Stiefelhagen, R., Bernardin, K., Rochet, C.: The CHIL audiovisual corpus for lecture and meeting analysis inside smart rooms. Lang. Resour. Eval. 41(3\u20134), 389\u2013407 (2007)","journal-title":"Lang. Resour. Eval."},{"key":"14_CR19","unstructured":"Pang, Z., Zhu, F.: Noise-robust ASR for the third \u2018CHiME\u2019 challenge exploiting time\u2013frequency masking based multi-channel speech enhancement and recurrent neural network (2015). arXiv:1509.07211"},{"key":"14_CR20","unstructured":"Parihar, N., Picone, J., Pearce, D., Hirsch, H.G.: Performance analysis of the Aurora large vocabulary baseline system. In: Proceedings of the 2004 European Signal Processing Conference (EUSIPCO), Vienna, pp.\u00a0553\u2013556 (2004)"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Pfeifenberger, L., Schrank, T., Z\u00f6hrer, M., Hagm\u00fcller, M., Pernkopf, F.: Multi-channel speech processing architectures for noise robust speech recognition: 3rd CHiME challenge results. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp. 452\u2013459 (2015)","DOI":"10.1109\/ASRU.2015.7404830"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Prudnikov, A., Korenevsky, M., Aleinik, S.: Adaptive beamforming and adaptive training of DNN acoustic models for enhanced multichannel noisy speech recognition. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp. 401\u2013408 (2015)","DOI":"10.1109\/ASRU.2015.7404823"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Renals, S., Hain, T., Bourlard, H.: Interpretation of multiparty meetings: the AMI and AMIDA projects. In: Proceedings of the 2nd Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), pp.\u00a0115\u2013118 (2008)","DOI":"10.1109\/HSCMA.2008.4538700"},{"key":"14_CR24","unstructured":"RWCP meeting speech corpus (RWCP-SP01) (2001). http:\/\/research.nii.ac.jp\/src\/en\/RWCP-SP01.html"},{"key":"14_CR25","volume-title":"The HIWIRE database, a noisy and non-native English speech corpus for cockpit communication","author":"J.C. Segura","year":"2007","unstructured":"Segura, J.C., Ehrette, T., Potamianos, A., Fohr, D., Illina, I., Breton, P.A., Clot, V., Gemello, R., Matassoni, M., Maragos, P.: The HIWIRE database, a noisy and non-native English speech corpus for cockpit communication (2007). http:\/\/islrn.org\/resources\/934-733-835-065-0\/"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Sivasankaran, S., Nugraha, A.A., Vincent, E., Morales-Cordovilla, J.A., Dalmia, S., Illina, I.: Robust ASR using neural network based speech enhancement and feature simulation. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp.\u00a0482\u2013489 (2015)","DOI":"10.1109\/ASRU.2015.7404834"},{"key":"14_CR27","unstructured":"Tachioka, Y., Watanabe, S., Le\u00a0Roux, J., Hershey, J.R.: Discriminative methods for noise robust speech recognition: a CHiME challenge benchmark. In: Proceedings of the 2nd CHiME Workshop on Machine Listening in Multisource Environments, Vancouver (2013)"},{"key":"14_CR28","unstructured":"Tachioka, Y., Kanagawa, H., Ishii, J.: The overview of the MELCO ASR system for the third CHiME challenge. Technical Report SVAN154551, Mitsubishi Electric (2015)"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Vesel\u00fd, K., Ghoshal, A., Burget, L., Povey, D.: Sequence-discriminative training of deep neural networks. In: Proceedings of INTERSPEECH, pp.\u00a02345\u20132349 (2013)","DOI":"10.21437\/Interspeech.2013-548"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Vincent, E., Barker, J., Watanabe, S., Le\u00a0Roux, J., Nesta, F., Matassoni, M.: The second \u2018CHiME\u2019 speech separation and recognition challenge: an overview of challenge systems and outcomes. In: Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp.\u00a0162\u2013167 (2013)","DOI":"10.1109\/ASRU.2013.6707723"},{"key":"14_CR31","volume-title":"The second \u2018CHiME\u2019 speech separation and recognition challenge: datasets, tasks and baselines","author":"E. Vincent","year":"2013","unstructured":"Vincent, E., Barker, J., Watanabe, S., Le Roux, J., Nesta, F., Matassoni, M.: The second \u2018CHiME\u2019 speech separation and recognition challenge: datasets, tasks and baselines. In: Proceedings of ICASSP (2013)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Vu, T.T., Bigot, B., Chng, E.S.: Speech enhancement using beamforming and non negative matrix factorization for robust speech recognition in the CHiME-3 challenge. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp.\u00a0423\u2013429 (2015)","DOI":"10.1109\/ASRU.2015.7404826"},{"key":"14_CR33","unstructured":"Wang, X., Wu, C., Zhang, P., Wang, Z., Liu, Y., Li, X., Fu, Q., Yan, Y.: Noise robust IOA\/CAS speech separation and recognition system for the third \u2018CHiME\u2019 challenge (2015). arXiv:1509.06103"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Yoshioka, T., Ito, N., Delcroix, M., Ogawa, A., Kinoshita, K., Fujimoto, M., Yu, C., Fabian, W.J., Espi, M., Higuchi, T., Araki, S., Nakatani, T.: The NTT CHiME-3 system: advances in speech enhancement and recognition for mobile multi-microphone devices. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp.\u00a0436\u2013443 (2015)","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, S., Xiao, X., Zhang, Z., Nguyen, T.N.T., Zhong, X., Ren, B., Wang, L., Jones, D.L., Chng, E.S., Li, H.: Robust speech recognition using beamforming with adaptive microphone gains and multichannel noise reduction. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, December 13\u201317, 2015, pp.\u00a0460\u2013467 (2015)","DOI":"10.1109\/ASRU.2015.7404831"},{"key":"14_CR36","unstructured":"Zhuang, Y., You, Y., Tan, T., Bi, M., Bu, S., Deng, W., Qian, Y., Yin, M., Yu, K.: System combination for multi-channel noise robust ASR. Technical Report SP2015-07, Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai (2015)"}],"container-title":["New Era for Robust Speech Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-64680-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T22:20:44Z","timestamp":1659738044000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-64680-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319646794","9783319646800"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-64680-0_14","relation":{},"subject":[],"published":{"date-parts":[[2017]]}}}