Yu, ChengzhuOgawa, A.Delcroix, M.Yoshioka, T.Nakatani, T.Hansen, John H. L.2016-10-272016-10-272015-09-062308-457Xhttp://hdl.handle.net/10735.1/5109In this study, we explore an i-vector based adaptation of deep neural network (DNN) in noisy environment. We first demonstrate the importance of encapsulating environment and channel variability into i-vectors for DNN adaptation in noisy conditions. To be able to obtain robust i-vector without losing noise and channel variability information, we investigate the use of parallel feature based i-vector extraction for DNN adaptation. Specifically, different types of features are used separately during two different stages of i-vector extraction namely universal background model (UBM) state alignment and i-vector computation. To capture noise and channel-specific feature variation, the conventional MFCC features are still used for i-vector computation. However, much more robust features such as Vector Taylor Series (VTS) enhanced as well as bottleneck features are exploited for UBM state alignment. Experimental results on Aurora-4 show that the parallel feature-based i-vectors yield performance gains of up to 9.2% relative compared to a baseline DNN-HMM system and 3.3% compared to a system using conventional MFCC-based i-vectors.en©2015 ISCAAcoustic modelsAutomatic speech recognitionNeural networks (Computer science)Vector analysisNoiseSpeech processingarticleYu, C., A. Ogawa, M. Delcroix, T. Yoshioka, et al. 2015. "Robust i-vector extraction for neural network adaptation in noisy environment." INTERSPEECH 2015 (16th Annual Conference Of The International Speech Communication Association), p. 2854-2857.2015