TY - JOUR AU - Liu, C. -. M. AU - Hsu, H. -. W. AU - Lee, W. -. C. PY - 2008 DA - 2008// TI - Compression artifacts in perceptual audio coding JO - IEEE Trans. Audio Speech Lang. Process. VL - 16 UR - https://doi.org/10.1109/TASL.2008.918979 DO - 10.1109/TASL.2008.918979 ID - Liu2008 ER - TY - JOUR AU - Van Son, R. J. J. H. PY - 2005 DA - 2005// TI - A study of pitch, formant, and spectral estimation errors introduced by three lossy speech compression algorithms JO - Acta Acustica United Acustica VL - 91 ID - Van Son2005 ER - TY - STD TI - C Barras, L Lamel, J Gauvain, in Acoustics, Speech, and Signal Processing. Proceedings of 2001 IEEE International Conference on, 1. Automatic transcription of compressed broadcast audio (Salt Lake City, USA, 2001), pp. 265–268. ID - ref3 ER - TY - STD TI - L Besacier, C Bergamini, D Vaufreydaz, E Castelli, in Multimedia Signal Processing. Proceedings of 2001 IEEE Fourth Workshop on. The effect of speech and audio compression on speech recognition performance (Cannes, France, 2001), pp. 301–306. ID - ref4 ER - TY - STD TI - PS Ng, I Sanches, in Proceedings of 2004 Conference Speech and Computer, SPEECOM. The influence of audio compression on speech recognition systems (St. Petersburg, Russia, September 2004). ID - ref5 ER - TY - STD TI - P Pollak, M Borsky, Communications in Computer and Information Science, in E-Business and Telecommunications. Small and large vocabulary speech recognition of MP3 data under real-word conditions: experimental study, vol.314 (SpringerBerlin, 2012), pp. 409–419. ID - ref6 ER - TY - STD TI - J Nouza, P Cerva, J Silovsky, in Acoustics, Speech and Signal Processing. Proceedings of 2013 IEEE International Conference on. Adding controlled amount of noise to improve recognition of compressed and spectrally distorted speech (Vancouver, Canada, May 2013), pp. 8046–8050. ID - ref7 ER - TY - STD TI - H Abbasian, B Nasersharif, A Akbari, M Rahmani, MS Moin, in Communications, Control and Signal Processing. 3rd International Symposium on. Optimized linear discriminant analysis for extracting robust speech features, (March 2008), pp. 819–824. ID - ref8 ER - TY - STD TI - S Tamura, S Hayamizu, in Signal Information Processing Association Annual Summit and Conference. 2012 Asia-Pacific. Multi-stream acoustic model adaptation for noisy speech recognition (Hollywood, USA, December 2012), pp. 1–4. ID - ref9 ER - TY - STD TI - U Remes, KJ Palomäki, M Kurimo, in EUSIPCO. Proceedings of 16th European Signal Processing Conference. Missing feature reconstruction And Acoustic Model Adaptation Combined For large vocabulary continuous speech recognition (Lausanne, Switzerland, 2008). ID - ref10 ER - TY - STD TI - D Yu, L Deng, Y Gong, A Acero, in Proceedings of the Interspeech. Discriminative training of variable-parameter HMMs for noise robust speech recognition (International Speech Communication AssociationBrisbane, Australia, September 2008). ID - ref11 ER - TY - STD TI - J Du, P Liu, F Soong, J-L Zhou, R-H Wang, Lecture Notes in Computer Science, in Chinese Spoken Language Processing. Noisy speech recognition performance of discriminative HMMs vol.4274 (SpringerBerlin, 2006), pp. 358–369. ID - ref12 ER - TY - CHAP AU - Povey, D. AU - Ghoshal, A. AU - Boulianne, G. AU - Burget, L. AU - Glembek, O. AU - Goel, N. AU - Hannemann, M. AU - Motlicek, P. AU - Qian, Y. AU - Schwarz, P. AU - Silovsky, J. AU - Stemmer, G. AU - Vesely, K. PY - 2011 DA - 2011// TI - The Kaldi speech recognition toolkit BT - IEEE 2011 Workshop on Automatic Speech Recognition and Understanding PB - IEEE Signal Processing Society CY - Hilton Waikoloa Village, Big Island, Hawaii, US ID - Povey2011 ER - TY - STD TI - R Hegemann, A Leidinger, R Brito, LAME (2011). http://lame.sourceforge.net UR - http://lame.sourceforge.net ID - ref14 ER - TY - STD TI - P Fousek, P Mizera, P Pollak, CtuCopy feature extraction tool (2014). http://noel.feld.cvut.cz/speechlab UR - http://noel.feld.cvut.cz/speechlab ID - ref15 ER - TY - JOUR AU - Prochazka, V. AU - Pollak, P. AU - Zdansky, J. AU - Nouza, J. PY - 2011 DA - 2011// TI - Performance of Czech speech recognition with language models created from public resources JO - Radioengineering VL - 20 ID - Prochazka2011 ER - TY - STD TI - Ústav Českého národního korpusu FF UK Praha, Český národní korpus - SYN2006PUB (2006). http://www.korpus.cz UR - http://www.korpus.cz ID - ref17 ER -