Please use this identifier to cite or link to this item:
|Title:||Towards knowledge-based features for HMM based large vocabulary automatic speech recognition|
|Source:||Launay, B.,Siohan, O.,Surendran, A.,Lee, C.-H. (2002). Towards knowledge-based features for HMM based large vocabulary automatic speech recognition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 1 : I/817-I/820. ScholarBank@NUS Repository.|
|Abstract:||This paper describes an attempt to design a knowledge-based large vocabulary speech recognition system. Our motivation is to replace features based on the short-term spectra, such as Mel-frequency cepstral coefficients (MFCC), by features that explicitly represent some of the distinctive features of the speech signal. However, rather than attempting to compute acoustic correlates of these distinctive features, we have engineered an approach where neural networks are trained to map short-term spectral features to the posterior probability of some distinctive features. These probabilities are then used as features in a large vocabulary tied-state HMM-based recognizer. Experimental results on the Wall Street Journal Task show that such a system, while not outperforming a MFCC-based system, generates very different error patterns. After combining the results of a baseline MFCC system with the results of several systems based on the proposed approach, we were able to obtain reductions in word error rates of 19% and 10% on the 5K and 20K tasks respectively over our best MFCC-based systems.|
|Source Title:||ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 16, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.