Pseudo 2-dimensional hidden Markov models in speech recognition
Tóm tắt
In this paper, the usage of pseudo 2-dimensional hidden Markov models for speech recognition is discussed. This image processing method should better model the time-frequency structure in speech signals. The method calculates the emission probability of a standard HMM by embedded HMM for each state. If a temporal sequence of spectral vectors is imagined as a spectrogram, this leads to a 2-dimensional warping of the spectrogram. This additional warping of the frequency axis could be useful for speaker-independent recognition and can be considered to be similar to a vocal tract normalization. The effects of this paradigm are investigated in this paper using the TI-Digits database.
Từ khóa
#Hidden Markov models #Speech recognition #Feature extraction #Image processing #Speech processing #Spectrogram #Computer science #Signal processing #Frequency #DatabasesTài liệu tham khảo
10.1002/j.1538-7305.1993.tb00655.x
bourlard, 2001, New Appreaches Towards Robust and Adaptive Speech Recognition, Advances in Neural Information Processing Systems 13
10.1109/ICASSP.1992.226254
eickeler, 1998, Improved Face Recognition Using Pseudo-2D Hidden Markov Models, Workshop on Advances in Facial Image Analysis and Recognition Technology in conjunction with 5th European Conference on Computer Vision
10.1109/ICASSP.1984.1172716
samaria, 1994, Face recognition using hidden Markov models
weber, 2000, HMM2- A novel approach to HMM emission probability estimation, ICSLP
hirsch, 2000, The Aurora Experimental Framework for the Performance Evaluation of Speech Recognition Systems under Noisy Conditions, Proc ISCA ITRW Workshop Automatic Speech Recognition (ASR), 181
rigoll, 1999, Statistical Pattern Recognition Techniques for Multimodal Human Computer Interaction and Multimedia Information Processing, Survey Paper Int Workshop Speech and Computer, 60