{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T11:58:56Z","timestamp":1774871936177,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319664286","type":"print"},{"value":"9783319664293","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\/978-3-319-66429-3_35","type":"book-chapter","created":{"date-parts":[[2017,8,12]],"date-time":"2017-08-12T02:02:55Z","timestamp":1502503375000},"page":"362-369","source":"Crossref","is-referenced-by-count":7,"title":["Experimenting with Hybrid TDNN\/HMM Acoustic Models for Russian Speech Recognition"],"prefix":"10.1007","author":[{"given":"Irina","family":"Kipyatkova","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,8,13]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-5779-3","volume-title":"Automatic Speech Recognition. A Deep Learning Approach","author":"D Yu","year":"2015","unstructured":"Yu, D., Deng, L.: Automatic Speech Recognition. A Deep Learning Approach. Springer, London (2015)"},{"issue":"6","key":"35_CR2","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sign. Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Sign. Process. Mag."},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Kipyatkova I., Karpov, A.: Variants of deep artificial neural networks for speech recognition systems. In: SPIIRAS Proceedings, vol. 6(49), pp. 80\u2013103 (2016). (in Russian) doi: http:\/\/dx.doi.org\/10.15622\/sp.49.5","DOI":"10.15622\/sp.49.5"},{"key":"35_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/ATSIP.2015.22","volume":"5","author":"L Deng","year":"2016","unstructured":"Deng, L.: Deep learning: from speech recognition to language and multimodal processing. APSIPA Trans. Sign. Inf. Process. 5, 1\u201315 (2016)","journal-title":"APSIPA Trans. Sign. Inf. Process."},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Seide, F., Li, G., Yu, D.: Conversational speech transcription using context-dependent deep neural networks. In: INTERSPEECH 2011, pp. 437\u2013 440 (2011)","DOI":"10.21437\/Interspeech.2011-169"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Delcroix, M., Kinoshita, K., Ogawa, A., Yoshioka, T., Tran, D., Nakatani, T.: Context adaptive neural network for rapid adaptation of deep CNN based acoustic models. In: INTERSPEECH 2016, pp. 1573\u20131577 (2016)","DOI":"10.21437\/Interspeech.2016-203"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Tran, D.T., Delcroix, M., Ogawa, A., Huemmer, C., Nakatani, T.: Feedback connection for deep neural network-based acoustic modeling. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2017), pp. 5240\u20135244 (2017)","DOI":"10.1109\/ICASSP.2017.7953156"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Geiger, J.T., Zhang, Z., Weninger, F., Schuller, B., Rigoll, G.: Robust speech recognition using long short-term memory recurrent neural networks for hybrid acoustic modelling. In: INTERSPEECH 2014, pp. 631\u2013635 (2014)","DOI":"10.21437\/Interspeech.2014-151"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Peddini, V., Povey, D., Khundanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: INTERSPEECH 2015, pp. 3214\u20133218 (2015)","DOI":"10.21437\/Interspeech.2015-647"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Tomashenko, N., Khokhlov, Y.: Speaker adaptation of context dependent deep neural networks based on MAP-adaptation and GMM-derived feature processing. In: INTERSPEECH 2014, pp. 2997\u20133001 (2014)","DOI":"10.21437\/Interspeech.2014-501"},{"key":"35_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-23132-7_29","volume-title":"Speech and Computer","author":"A Prudnikov","year":"2015","unstructured":"Prudnikov, A., Medennikov, I., Mendelev, V., Korenevsky, M., Khokhlov, Y.: Improving acoustic models for Russian spontaneous speech recognition. In: Ronzhin, A., Potapova, R., Fakotakis, N. (eds.) SPECOM 2015. LNCS(LNAI), vol. 9319, pp. 234\u2013242. Springer, Cham (2015). doi: 10.1007\/978-3-319-23132-7_29"},{"key":"35_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/978-3-319-43958-7_29","volume-title":"Speech and Computer","author":"I Kipyatkova","year":"2016","unstructured":"Kipyatkova, I., Karpov, A.: DNN-based acoustic modeling for Russian speech recognition using kaldi. In: Ronzhin, A., Potapova, R., N\u00e9meth, G. (eds.) SPECOM 2016. LNCS, vol. 9811, pp. 246\u2013253. Springer, Cham (2016). doi: 10.1007\/978-3-319-43958-7_29"},{"key":"35_CR13","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE Workshop on Automatic Speech Recognition and Understanding ASRU (2011)"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Saon, G., Soltau, H., Nahamoo, D., Picheny, M.: Speaker adaptation of neural network acoustic models using i-Vectors. In: IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 55\u201359 (2013)","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"35_CR15","unstructured":"Povey, D., Zhang, X., Khudanpur, S.: Parallel training of DNNs with natural gradient and parameter averaging (2014). Preprint: arXiv:1410.7455 , http:\/\/arxiv.org\/pdf\/1410.7455v8.pdf"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Zhang X., Trmal J., Povey D., Khudanpur S.: Improving deep neural network acoustic models using generalized maxout networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 215\u2013219 (2014)","DOI":"10.1109\/ICASSP.2014.6853589"},{"issue":"1","key":"35_CR17","first-page":"29","volume":"1","author":"AV Gapochkin","year":"2014","unstructured":"Gapochkin, A.V.: Neural networks in speech recognition systems. Sci. Time 1(1), 29\u201336 (2014). (in Russian)","journal-title":"Sci. Time"},{"issue":"3","key":"35_CR18","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1109\/29.21701","volume":"37","author":"A Waibel","year":"1989","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.: Phoneme recognition using time-delay neural networks. IEEE Trans. Acoust. Speech Sign. Process. 37(3), 328\u2013339 (1989)","journal-title":"IEEE Trans. Acoust. Speech Sign. Process."},{"key":"35_CR19","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.specom.2013.07.004","volume":"56","author":"A Karpov","year":"2014","unstructured":"Karpov, A., Markov, K., Kipyatkova, I., Vazhenina, D., Ronzhin, A.: Large vocabulary Russian speech recognition using syntactico-statistical language modeling. Speech Commun. 56, 213\u2013228 (2014)","journal-title":"Speech Commun."},{"key":"35_CR20","unstructured":"Stolcke, A., Zheng, J., Wang, W., Abrash, V.: SRILM at sixteen: update and outlook. In: Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop ASRU 2011 (2011)"},{"key":"35_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/978-3-319-01931-4_29","volume-title":"Speech and Computer","author":"I Kipyatkova","year":"2013","unstructured":"Kipyatkova, I., Karpov, A.: Lexicon size and language model order optimization for Russian LVCSR. In: \u017delezn\u00fd, M., Habernal, I., Ronzhin, A. (eds.) SPECOM 2013. LNCS(LNAI), vol. 8113, pp. 219\u2013226. Springer, Cham (2013). doi: 10.1007\/978-3-319-01931-4_29"},{"issue":"1","key":"35_CR22","first-page":"11","volume":"10","author":"I Kipyatkova","year":"2013","unstructured":"Kipyatkova, I., Karpov, A., Verkhodanova, V., Zelezny, M.: Modeling of pronunciation, language and nonverbal units at conversational russian speech recognition. Int. J. Comput. Sci. Appl. 10(1), 11\u201330 (2013)","journal-title":"Int. J. Comput. Sci. Appl."},{"key":"35_CR23","unstructured":"Jokisch, O., Wagner, A., Sabo, R., Jaeckel, R., Cylwik, N., Rusko, M., Ronzhin A., Hoffmann, R.: Multilingual speech data collection for the assessment of pronunciation and prosody in a language learning system. In: Proceedings of SPECOM 2009, pp. 515\u2013520 (2009)"},{"key":"35_CR24","unstructured":"State Standard P\u00a050840\u201395. Speech transmission by communication paths. Evaluation methods of quality, intelligibility and recognizability, p. 230. Standartov Publ., Moscow (1996). (in Russian)"},{"key":"35_CR25","unstructured":"Stepanova, S.B.: Phonetic features of Russian speech: realization and transcription, Ph.D. thesis (1988). (in Russian)"},{"key":"35_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1007\/978-3-319-43958-7_40","volume-title":"Speech and Computer","author":"V Verkhodanova","year":"2016","unstructured":"Verkhodanova, V., Ronzhin, A., Kipyatkova, I., Ivanko, D., Karpov, A., \u017delezn\u00fd, M.: HAVRUS corpus: high-speed recordings of audio-visual Russian speech. In: Ronzhin, A., Potapova, R., N\u00e9meth, G. (eds.) SPECOM 2016. LNCS, vol. 9811, pp. 338\u2013345. Springer, Cham (2016). doi: 10.1007\/978-3-319-43958-7_40"},{"issue":"3","key":"35_CR27","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1134\/S1054661809030225","volume":"19","author":"AA Karpov","year":"2009","unstructured":"Karpov, A.A., Ronzhin, A.L.: Information enquiry kiosk with multimodal user interface. Pattern Recogn. Image Anal. 19(3), 546\u2013558 (2009)","journal-title":"Pattern Recogn. Image Anal."},{"issue":"5","key":"35_CR28","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1134\/S0005117917050083","volume":"78","author":"I Kipyatkova","year":"2017","unstructured":"Kipyatkova, I., Karpov, A.: A study of neural network Russian language models for automatic continuous speech recognition systems. Autom. Remote Control 78(5), 858\u2013867 (2017). Springer","journal-title":"Autom. Remote Control"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-66429-3_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:50:51Z","timestamp":1692924651000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-66429-3_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319664286","9783319664293"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-66429-3_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}