{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T04:15:53Z","timestamp":1729052153611},"reference-count":30,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1587\/transfun.2022eap1130","type":"journal-article","created":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T22:11:11Z","timestamp":1677535871000},"page":"1224-1233","source":"Crossref","is-referenced-by-count":0,"title":["Low-Complexity and Accurate Noise Suppression Based on an a Priori SNR Model for Robust Speech Recognition on Embedded Systems and Its Evaluation in a Car Environment"],"prefix":"10.1587","volume":"E106.A","author":[{"given":"Masanori","family":"TSUJIKAWA","sequence":"first","affiliation":[{"name":"Department of Electrical Electronic and Information Engineering, Faculty of Engineering Science, Kansai University"},{"name":"Biometrics Research Laboratories, NEC Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshinobu","family":"KAJIKAWA","sequence":"additional","affiliation":[{"name":"Department of Electrical Electronic and Information Engineering, Faculty of Engineering Science, Kansai University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] S.F. Boll, \u201cSuppression of acoustic noise in speech using spectral subtraction,\u201d IEEE Trans. Acoust., Speech, Signal Process., vol.27, no.2, pp.113-120, April 1979. 10.1109\/tassp.1979.1163209","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] J.S. Lim and A.V. Oppenheim, \u201cEnhancement and bandwidth compression of speech,\u201d Proc. IEEE, vol.67, no.12, pp.1586-1604, Dec. 1979. 10.1109\/proc.1979.11540","DOI":"10.1109\/PROC.1979.11540"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] Y. Ephraim and D. Malah, \u201cSpeech enhancement using a minimum mean-square error short-time spectral amplitude estimator,\u201d IEEE Trans. Acoust., Speech, Signal Process., vol.ASSP-32, no.6, pp.1109-1121, Dec. 1984. 10.1109\/tassp.1984.1164453","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] M. Kato, A. Sugiyama, and M. Serizawa, \u201cNoise suppression with high speech quality based on weighted noise estimation and MMSE STSA,\u201d Electronics and Communications in Japan, vol.89, no.2, pp.43-53, 2006. 10.1002\/ecjc.20145","DOI":"10.1002\/ecjc.20145"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] Y. Ephraim and D. Malah, \u201cSpeech enhancement using a minimum mean-square error log-spectral amplitude estimator,\u201d IEEE Trans. Acoust., Speech, Signal Process., vol.33, no.2, pp.443-445, April 1985. 10.1109\/tassp.1985.1164550","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] I. Cohen and B. Berdugo, \u201cSpeech enhancement for non-stationary noise environments,\u201d Signal Processing, vol.81, no.11, pp.2403-2418, 2001. 10.1016\/s0165-1684(01)00128-1","DOI":"10.1016\/S0165-1684(01)00128-1"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] Y. Obuchi, R. Takeda, and M. Togami, \u201cNoise suppression method for preprocessor of time-lag speech recognition system based on bidirectional optimally modified log spectral amplitude estimation,\u201d Acoustical Science and Technology, vol.34, no.2, pp.133-141, 2013. 10.1250\/ast.34.133","DOI":"10.1250\/ast.34.133"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] R. Martin, \u201cNoise power spectral density estimation based on optimal smoothing and minimum statistics,\u201d IEEE Trans. Speech Audio Process., vol.9, no.5, pp.504-512, July 2001. 10.1109\/89.928915","DOI":"10.1109\/89.928915"},{"key":"9","unstructured":"[9] ETSI, \u201cSpeech processing, transmission and quality aspects(STQ); distributed speech recognition; advanced front-end feature extraction algorithm; compression algorithms,\u201d ETSI ES 202 050 v1.1.1, 2002."},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] D. Macho, L. Mauuary, B. Noe, Y.M. Cheng, D. Ealey, D. Jouvet, H. Kelleher, D. Pearce, and F. Saadoun, \u201cEvaluation of a noise-robust DSR front-end on AURORA databases,\u201d Proc. ICSLP 2002, Sept. 2002. 10.21437\/icslp.2002-3","DOI":"10.21437\/ICSLP.2002-3"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] J. Du, L. Dai, and Q. Huo, \u201cSynthesized stereo mapping via deep neural networks for noisy speech recognition,\u201d Proc. ICASSP 2014, pp.1764-1768, May 2014. 10.1109\/icassp.2014.6853901","DOI":"10.1109\/ICASSP.2014.6853901"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] H. Zhang, C. Liu, N. Inoue, and K. Shinoda, \u201cMulti-task autoencoder for noise-robust speech recognition,\u201d Proc. ICASSP 2018, pp.5599-5603, April 2018. 10.1109\/icassp.2018.8461446","DOI":"10.1109\/ICASSP.2018.8461446"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] H. Erdogan, J.R. Hershey, S. Watanabe, and J. Le Roux, \u201cPhase-sensitive and recognition-boosted speech separation using deep recurrent neural networks,\u201d Proc. ICASSP 2015, pp.708-712, April 2018. 10.1109\/icassp.2015.7178061","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] D. Wang, J. Chen, \u201cSupervised speech separation based on deep learning: An overview,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.26, no.10, pp.1702-1726, Oct. 2018. 10.1109\/taslp.2018.2842159","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] Q. Wang, K.A. Lee, T. Koshinaka, K. Okabe, and H. Yamamoto, \u201cTask-aware warping factors in mask-based speech enhancement,\u201d Proc. 2021 29th European Signal Processing Conference (EUSIPCO), pp.476-480, Aug. 2021. 10.23919\/eusipco54536.2021.9616081","DOI":"10.23919\/EUSIPCO54536.2021.9616081"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] P.J. Moreno, B. Raj, and R.M. Stern, \u201cA vector Taylor series approach for environment-independent speech recognition,\u201d Proc. ICASSP 1996, pp.733-736, May 1996. 10.1109\/icassp.1996.543225","DOI":"10.1109\/ICASSP.1996.543225"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] J. Droppo, L. Deng, and A. Acero, \u201cA comparison of three non-linear observation models for noisy speech features,\u201d Proc. Eurospeech 2003, pp.681-684, Sept. 2003. 10.21437\/eurospeech.2003-295","DOI":"10.21437\/Eurospeech.2003-295"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] O. Ichikawa, S.J. Rennie, T. Fukuda, and M. Nishimura, \u201cModel-based noise reduction leveraging frequency-wise confidence metric for in-car speech recognition,\u201d Proc. ICASSP 2012, pp.4921-4924, March 2012. 10.1109\/icassp.2012.6289023","DOI":"10.1109\/ICASSP.2012.6289023"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] M. Fujimoto, S. Watanabe, and T. Nakatani, \u201cA robust estimation method of noise mixture model for noise suppression,\u201d Proc. Interspeech 2011, pp.697-700, 2011. 10.21437\/interspeech.2011-207","DOI":"10.21437\/Interspeech.2011-207"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] M. Fujimoto and T. Nakatani, \u201cFeature enhancement based on generative-discriminative hybrid approach with GMMs and DNNs for noise robust speech recognition,\u201d Proc. ICASSP 2015, pp.5019-5023, April 2015. 10.1109\/icassp.2015.7178926","DOI":"10.1109\/ICASSP.2015.7178926"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] T. Arakawa, M. Tsujikawa, and R. Isotani, \u201cModel-based Wiener filter for noise robust speech recognition,\u201d Proc. ICASSP 2006, pp.537-540, May 2006. 10.1109\/icassp.2006.1660076","DOI":"10.1109\/ICASSP.2006.1660076"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] Z. Yan and F.K. Soong, \u201cWord graph based feature enhancement for noisy speech recognition,\u201d Proc. ICASSP 2007, pp.373-376, April 2007. 10.1109\/icassp.2007.366927","DOI":"10.1109\/ICASSP.2007.366927"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] M. Tsujikawa, T. Arakawa, and R. Isotani, \u201cIn-car speech recognition using model-based Wiener filter and multi-condition training,\u201d Proc. Interspeech 2008, pp.972-975, Sept. 2008. 10.21437\/interspeech.2008-284","DOI":"10.21437\/Interspeech.2008-284"},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] M. Fujimoto and K. Ishizuka, \u201cNoise robust voice activity detection based on switching Kalman filter,\u201d IEICE Trans. Inf & Syst., vol.E91-D, no.3, pp.467-477, March 2008. 10.1093\/ietisy\/e91-d.3.467","DOI":"10.1093\/ietisy\/e91-d.3.467"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] S. Nakamura, M. Fujimoto, and K. Takeda, \u201cCENSREC2: Corpus and evaluation environments for in car continuous digit speech recognition,\u201d Proc. Interspeech 2006, pp.2330-2333, Sept. 2006. 10.21437\/interspeech.2006-99","DOI":"10.21437\/Interspeech.2006-99"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] M. Fujimoto, K. Takeda, and S. Nakamura, \u201cCENSREC3: An evaluation framework for Japanese speech recognition in real car-driving environments,\u201d IEICE Trans. Inf. & Syst., vol.E89-D, no.11, pp.2783-2793, Nov. 2006. 10.1093\/ietisy\/e89-d.11.2783","DOI":"10.1093\/ietisy\/e89-d.11.2783"},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] E. Principi, S. Cifani, R. Rotili, S. Squartini, and F. Piazza, \u201cComparative evaluation of single-channel MMSE-based noise reduction schemes for speech recognition,\u201d Journal of Electrical and Computer Engineering, vol.2010, pp.1-6, 2010. 10.1155\/2010\/962103","DOI":"10.1155\/2010\/962103"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] J. Du, Q. Wang, T. Gao, Y. Xu, L. Dai, and C. Lee, \u201cRobust speech recognition with speech enhanced deep neural networks,\u201d Proc. Interspeech 2014, pp.616-620, 2014. 10.21437\/interspeech.2014-148","DOI":"10.21437\/Interspeech.2014-148"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] W. Li and H. Bourlard, \u201cNon-linear spectral contrast stretching for in-car speech recognition,\u201d Proc. Interspeech 2007, pp.1122-1125, 2007. 10.21437\/interspeech.2007-367","DOI":"10.21437\/Interspeech.2007-367"},{"key":"30","unstructured":"[30] Texas Instruments Inc., \u201cTMS320C6748 DSP development kit (LCDK),\u201d https:\/\/www.ti.com\/tool\/TMDSLCDK6748, Access Oct. 1st 2022."}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E106.A\/9\/E106.A_2022EAP1130\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T08:38:34Z","timestamp":1728981514000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E106.A\/9\/E106.A_2022EAP1130\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":30,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2022eap1130","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"type":"print","value":"0916-8508"},{"type":"electronic","value":"1745-1337"}],"subject":[],"published":{"date-parts":[[2023,9,1]]},"article-number":"2022EAP1130"}}