{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:12:59Z","timestamp":1748491979187,"version":"3.41.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,6,30]],"date-time":"2015-06-30T00:00:00Z","timestamp":1435622400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/s13634-015-0241-y","type":"journal-article","created":{"date-parts":[[2015,6,29]],"date-time":"2015-06-29T03:38:44Z","timestamp":1435549124000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Effectiveness of dereverberation, feature transformation, discriminative training methods, and system combination approach for various reverberant environments"],"prefix":"10.1186","volume":"2015","author":[{"given":"Yuuki","family":"Tachioka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Narita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,6,30]]},"reference":[{"key":"241_CR1","doi-asserted-by":"crossref","unstructured":"K Kinoshita, M Delcroix, T Yoshioka, T Nakatani, E Habets, R Haeb-Umbach, V Leutnant, A Sehr, W Kellermann, R Maas, S Gannot, B Raj, in Proceedings of WASPAA. The REVERB Challenge: A common evaluation framework for dereverberation and recognition of reverberant speech (IEEE, 2013).","DOI":"10.1109\/WASPAA.2013.6701894"},{"issue":"3","key":"241_CR2","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1250\/ast.34.212","volume":"34","author":"Y Tachioka","year":"2013","unstructured":"Y Tachioka, T Hanazawa, T Iwasaki, Dereverberation method with reverberation time estimation using floored ratio of spectral subtraction. Acoust. Sci. Technol. 34(3), 212\u2013215 (2013).","journal-title":"Acoust. Sci. Technol."},{"key":"241_CR3","volume-title":"Array Signal Processing","author":"D Johnson","year":"1993","unstructured":"D Johnson, D Dudgeon, Array Signal Processing (Prentice-Hall, New Jersey, 1993)."},{"key":"241_CR4","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1109\/TASSP.1976.1162830","volume":"24","author":"C Knapp","year":"1976","unstructured":"C Knapp, G Carter, The generalized correlation method for estimation of time delay. IEEE Trans. Acous. Speech, and Signal Process. 24, 320\u2013327 (1976).","journal-title":"IEEE Trans. Acous. Speech, and Signal Process."},{"key":"241_CR5","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1250\/ast.33.68","volume":"33","author":"Y Tachioka","year":"2012","unstructured":"Y Tachioka, T Narita, T Iwasaki, Direction of arrival estimation by cross-power spectrum phase analysis using prior distributions and voice activity detection information. Acoust. Sci. Technol. 33, 68\u201371 (2012).","journal-title":"Acoust. Sci. Technol."},{"key":"241_CR6","doi-asserted-by":"crossref","unstructured":"D Povey, P Woodland, in Proceedings of ICASSP, I. Minimum phone error and I-smoothing for improved discriminative training (IEEE, 2002), pp. 105\u2013108.","DOI":"10.1109\/ICASSP.2002.1005687"},{"key":"241_CR7","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1109\/TASL.2006.876778","volume":"15","author":"E McDermott","year":"2007","unstructured":"E McDermott, T Hazen, J Le Roux, A Nakamura, S Katagiri, Discriminative training for large-vocabulary speech recognition using minimum classification error. IEEE Trans. Audio Speech Lang. Process. 15, 203\u2013223 (2007).","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"241_CR8","doi-asserted-by":"crossref","unstructured":"R Haeb-Umbach, H Ney, in Proceedings of ICASSP. Linear discriminant analysis for improved large vocabulary continuous speech recognition (IEEE, 1992), pp. 13\u201316.","DOI":"10.1109\/ICASSP.1992.225984"},{"key":"241_CR9","doi-asserted-by":"crossref","unstructured":"R Gopinath, in Proceedings of ICASSP. Maximum likelihood modeling with Gaussian distributions for classification (IEEE, 1998), pp. 661\u2013664.","DOI":"10.1109\/ICASSP.1998.675351"},{"key":"241_CR10","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/89.759034","volume":"7","author":"M Gales","year":"1999","unstructured":"M Gales, Semi-tied covariance matrices for hidden Markov models. IEEE Trans. Speech Audio Process. 7, 272\u2013281 (1999).","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"241_CR11","doi-asserted-by":"crossref","unstructured":"T Anastasakos, J McDonough, R Schwartz, J Makhoul, in Proceedings of ICSLP. A compact model for speaker-adaptive training (ISCA, 1996), pp. 1137\u20131140.","DOI":"10.21437\/ICSLP.1996-253"},{"key":"241_CR12","doi-asserted-by":"crossref","unstructured":"D Povey, B Kingsbury, L Mangu, G Saon, H Soltau, G Zweig, in Proceedings of ICASSP. fMPE: Discriminatively trained features for speech recognition (IEEE, 2005), pp. 961\u2013964.","DOI":"10.1109\/ICASSP.2005.1415275"},{"key":"241_CR13","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"28","author":"G Hinton","year":"2012","unstructured":"G Hinton, L Deng, D Yu, G Dahl, A Mohamed, N Jaitly, A Senior, V Vanhoucke, P Nguyen, T Sainath, B Kingsbury, Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process. Mag. 28, 82\u201397 (2012).","journal-title":"IEEE Signal Process. Mag."},{"key":"241_CR14","doi-asserted-by":"crossref","unstructured":"E Vincent, J Barker, S Watanabe, Le Roux, J, F Nesta, M Matassoni, in Proceedings of ICASSP. The second \u2018CHiME\u2019 speech separation and recognition challenge: Datasets, tasks and baselines (IEEE, 2013), pp. 126\u2013130.","DOI":"10.1109\/ICASSP.2013.6637622"},{"key":"241_CR15","doi-asserted-by":"crossref","unstructured":"Y Tachioka, S Watanabe, J Hershey, in Proceedings of ICASSP. Effectiveness of discriminative training and feature transformation for reverberated and noisy speech (IEEE, 2013), pp. 6935\u20136939.","DOI":"10.1109\/ICASSP.2013.6639006"},{"key":"241_CR16","unstructured":"Y Tachioka, S Watanabe, J Le Roux, J Hershey, in Proceedings of the 2nd CHiME Workshop on Machine Listening in Multisource Environments. Discriminative methods for noise robust speech recognition: A CHiME challenge benchmark, (2013), pp. 19\u201324."},{"key":"241_CR17","doi-asserted-by":"crossref","unstructured":"H Christensen, J Barker, N Ma, P Green, in Proceedings of INTERSPEECH. The CHiME corpus: a resource and a challenge for computational hearing in multisource environments (ISCA, 2010), pp. 1918\u20131921.","DOI":"10.21437\/Interspeech.2010-552"},{"key":"241_CR18","doi-asserted-by":"crossref","unstructured":"G Saon, S Dharanipragada, D Povey, in Proceedings of ICASSP, I. Feature space Gaussianization (IEEE, 2004), pp. 329\u2013332.","DOI":"10.1109\/ICASSP.2004.1325989"},{"key":"241_CR19","unstructured":"K Palom\u00e4ki, H Kallasjoki, in Proceedings of REVERB Workshop. Reverberation robust speech recognition by matching distributions of spectrally and temporally decorrelated features, (2014)."},{"key":"241_CR20","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.csl.2011.04.002","volume":"26","author":"D Povey","year":"2012","unstructured":"D Povey, K Yao, A basis representation of constrained MLLR transforms for robust adaptation. Comput. Speech and Language. 26, 35\u201351 (2012).","journal-title":"Comput. Speech and Language."},{"key":"241_CR21","doi-asserted-by":"crossref","unstructured":"A Mohamed, G Hinton, G Penn, in Proceedings of ICASSP. Understanding how deep belief networks perform acoustic modelling (IEEE, 2012), pp. 4273\u20134276.","DOI":"10.1109\/ICASSP.2012.6288863"},{"key":"241_CR22","unstructured":"J Fiscus, in Proceedings of ASRU. A post-processing system to yield reduced error word rates: Recognizer output voting error reduction (ROVER) (IEEE, 1997), pp. 347\u2013354."},{"key":"241_CR23","unstructured":"G Evermann, P Woodland, in Proceedings of NIST Speech Transcription Workshop. Posterior probability decoding, confidence estimation and system combination, (2000)."},{"key":"241_CR24","doi-asserted-by":"crossref","unstructured":"B Hoffmeister, T Klein, R Schl\u00fcter, H Ney, in Proceedings of ICSLP. Frame based system combination and a comparison with weighted ROVER and CNC (ISCA, 2006), pp. 537\u2013540.","DOI":"10.21437\/Interspeech.2006-203"},{"key":"241_CR25","doi-asserted-by":"crossref","unstructured":"F Diehl, P Woodland, in Proceedings of INTERSPEECH. Complementary phone error training (ISCA, 2012).","DOI":"10.21437\/Interspeech.2012-499"},{"issue":"3","key":"241_CR26","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1109\/TASLP.2014.2303295","volume":"22","author":"K Audhkhasi","year":"2014","unstructured":"K Audhkhasi, A Zavou, P Georgiou, S Narayanan, Theoretical analysis of diversity in an ensemble of automatic speech recognition systems. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(3), 711\u2013726 (2014).","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"241_CR27","doi-asserted-by":"crossref","unstructured":"Y Tachioka, S Watanabe, in Proceedings of INTERSPEECH. Discriminative training of acoustic models for system combination (ISCA, 2013), pp. 2355\u20132359.","DOI":"10.1109\/ASRU.2013.6707703"},{"key":"241_CR28","doi-asserted-by":"crossref","unstructured":"Y Tachioka, S Watanabe, J Le Roux, J Hershey, in Proceedings of ASRU. A generalized framework of discriminative training for system combination (IEEE, 2013), pp. 43\u201348.","DOI":"10.1109\/ASRU.2013.6707703"},{"issue":"2","key":"241_CR29","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.csl.2010.06.003","volume":"25","author":"D Povey","year":"2011","unstructured":"D Povey, L Burget, M Agarwal, P Akyazi, F Kai, A Ghoshal, O Glembek, N Goel, M Karafi\u00e1t, A Rastrow, R Rose, P Schwarz, S Thomas, The subspace Gaussian mixture model \u2013a structured model for speech recognition. Comput. Speech Lang. 25(2), 404\u2013439 (2011).","journal-title":"Comput. Speech Lang."},{"key":"241_CR30","unstructured":"Y Tachioka, T Narita, S Watanabe, F Weninger, in Proceedings of REVERB Challenge. Dual system combination approach for various reverberant environments, (2014), pp. 1\u20138."},{"issue":"10","key":"241_CR31","first-page":"513","volume":"65","author":"T Suzuki","year":"2009","unstructured":"T Suzuki, Y Kaneda, Sound source direction estimation based on subband peak-hold processing. J. Acoust. Soc. Japan. 65(10), 513\u2013522 (2009).","journal-title":"J. Acoust. Soc. Japan"},{"key":"241_CR32","doi-asserted-by":"crossref","unstructured":"T Nishiura, T Yamada, T Nakamura, K Shikano, in Proceedings of ICASSP, 2. Localization of multiple sound sources based on a CSP analysis with a microphone array (IEEE, 2000), pp. 1053\u20131056.","DOI":"10.1109\/ICASSP.2000.859144"},{"key":"241_CR33","volume-title":"Speech Dereverberation","author":"E Habets","year":"2010","unstructured":"E Habets, in Speech Dereverberation, ed. by P Naylor, N Gaubitch. Speech dereverberation using statistical reverberation models (SpringerLondon, 2010)."},{"issue":"2","key":"241_CR34","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"S Boll","year":"1979","unstructured":"S Boll, Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Acous. Speech Signal Process. 27(2), 113\u2013120 (1979).","journal-title":"IEEE Trans. Acous. Speech Signal Process."},{"key":"241_CR35","doi-asserted-by":"publisher","DOI":"10.1002\/9780470374122","volume-title":"Adaptive Filters","author":"AH Sayed","year":"2008","unstructured":"AH Sayed, Adaptive Filters (John Wiley & Sons, New Jersey, 2008)."},{"key":"241_CR36","doi-asserted-by":"crossref","unstructured":"D Povey, D Kanevsky, B Kingsbury, B Ramabhadran, G Saon, K Visweswariah, in Proceedings of ICASSP. Boosted MMI for model and feature-space discriminative training (IEEE, 2008), pp. 4057\u20134060.","DOI":"10.1109\/ICASSP.2008.4518545"},{"key":"241_CR37","doi-asserted-by":"crossref","unstructured":"D Povey, in Proceedings of INTERSPEECH. Improvements to fMPE for discriminative training of features (ISCA, 2005), pp. 2977\u20132980.","DOI":"10.21437\/Interspeech.2005-133"},{"key":"241_CR38","doi-asserted-by":"crossref","unstructured":"Vesely, K\u0301, A Ghoshal, L Burget, D Povey, in Proceedings of INTERSPEECH. Sequence-discriminative training of deep neural networks, (2013).","DOI":"10.21437\/Interspeech.2013-548"},{"key":"241_CR39","doi-asserted-by":"crossref","unstructured":"T Robinson, J Fransen, D Pye, J Foote, S Renals, in Proceedings of ICASSP. WSJCAMO: a British English speech corpus for large vocabulary continuous speech recognition (IEEE, 1995), pp. 81\u201384.","DOI":"10.1109\/ICASSP.1995.479278"},{"key":"241_CR40","unstructured":"D Povey, A Ghoshal, G Boulianne, L Burget, O Glembek, N Goel, M Hannemann, M Petr, Y Qian, P Schwarz, J Silovsk\u00fd, G Stemmer, K Vesel\u00fd, in Proceedings of ASRU. The Kaldi speech recognition toolkit (IEEE, 2011), pp. 1\u20134."},{"key":"241_CR41","doi-asserted-by":"crossref","unstructured":"H Xu, D Povey, L Mangu, J Zhu, in Proceedings of ICASSP. An improved consensus-like method for minimum Bayes risk decoding and lattice combination (IEEE, 2010), pp. 4938\u20134941.","DOI":"10.1109\/ICASSP.2010.5495100"},{"key":"241_CR42","unstructured":"J Snoek, H Larochelle, R Adams, in Proceedings of Neural Information Processing Systems. Practical bayesian optimization of machine learning algorithms, (2012)."},{"key":"241_CR43","doi-asserted-by":"crossref","unstructured":"G Dahl, T Sainath, G Hinton, in Proceedings of ICASSP. Improving deep neural networks for LVCSR using rectified linear units and dropout (IEEE, 2013), pp. 8609\u20138613.","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"241_CR44","doi-asserted-by":"crossref","unstructured":"S Watanabe, J Le Roux, in Proceedings of ICASSP. Black box optimization for automatic speech recognition (IEEE, 2014), pp. 3280\u20133284.","DOI":"10.1109\/ICASSP.2014.6854202"},{"key":"241_CR45","doi-asserted-by":"crossref","unstructured":"F Weninger, S Watanabe, Y Tachioka, B Schuller, in Proceedings of ICASSP. Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition (IEEE, 2014), pp. 4656\u20134660.","DOI":"10.1109\/ICASSP.2014.6854478"},{"key":"241_CR46","unstructured":"F Weninger, S Watanabe, J Le Roux, J Hershey, Y Tachioka, JT Geiger, BW Schuller, G Rigoll, in Proceedings of REVERB Challenge. The MERL\/MELCO\/TUM system using deep recurrent neural network speech enhancement, (2014), pp. 1\u20138."},{"key":"241_CR47","unstructured":"X Xiao, Z Shengkui, DHH Nguyen, Z Xionghu, D Jones, E-S Chng, H Li, in Proceedings of REVERB Challenge. The NTU-ADSC systems for reverberation challenge 2014, (2014), pp. 1\u20138."},{"key":"241_CR48","unstructured":"MJ Alam, V Gupta, P Kenny, P Dumouchel, in Proceedings of REVERB Challenge. Use of multiple front-ends and i-vector-based speaker adaptation for robust speech recognition, (2014), pp. 1\u20138."},{"key":"241_CR49","unstructured":"M Delcroix, T Yoshioka, A Ogawa, Y Kubo, M Fujimoto, I Nobutaka, K Kinoshita, M Espi, T Hori, T Nakatani, A Nakamura, in Proceedings of REVERB Challenge. Linear prediction-based dereverberation with advanced speech enhancement and recognition technologies for the REVERB challenge, (2014), pp. 1\u20138."}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13634-015-0241-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0241-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0241-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0241-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T22:20:51Z","timestamp":1748470851000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-015-0241-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,30]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["241"],"URL":"https:\/\/doi.org\/10.1186\/s13634-015-0241-y","relation":{},"ISSN":["1687-6180"],"issn-type":[{"type":"electronic","value":"1687-6180"}],"subject":[],"published":{"date-parts":[[2015,6,30]]},"assertion":[{"value":"6 February 2015","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2015","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2015","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"52"}}