Title :
Layered markov models: a new architectural approach to automatic speech recognition
Author :
Penagarikano, Mikel ; Bordel, German
Author_Institution :
Dept. of Electr. & Electron., Basque Country Univ., Leioa
fDate :
Sept. 29 2004-Oct. 1 2004
Abstract :
This paper presents the theoretical basis of layered Markov models (LMM), which integrate all the knowledge levels commonly used in automatic speech recognition (acoustic, lexical and language levels) in a single model. Each knowledge level is represented by a set of Markov models (or even hidden Markov models) and all these sets are arranged in a layered structure. Given that common supervised training and recognition paradigms can be also expressed as simple Markov models, they can be formalized and integrated into the model as an extra knowledge layer. In addition, it is shown that hidden Markov models (HMM) and newer HMM2 can be considered as particular instances of LMM
Keywords :
hidden Markov models; knowledge representation; learning (artificial intelligence); speech recognition; automatic speech recognition; hidden Markov models; knowledge level; layered Markov models; recognition paradigms; supervised training; Automata; Automatic speech recognition; Electronic mail; Hidden Markov models; Metastasis; Natural languages; Speech recognition;
Conference_Titel :
Machine Learning for Signal Processing, 2004. Proceedings of the 2004 14th IEEE Signal Processing Society Workshop
Conference_Location :
Sao Luis
Print_ISBN :
0-7803-8608-4
DOI :
10.1109/MLSP.2004.1422988