The application of hidden Markov models in speech recognition
The Application of Hidden Markov Models in Speech Recognition Page 1 The Application of
Hidden Markov Models in Speech Recognition Full text available at: http://dx.doi.org/10.1561/2000000004 …
Hidden Markov Models in Speech Recognition Full text available at: http://dx.doi.org/10.1561/2000000004 …
Boosted MMI for model and feature-space discriminative training
We present a modified form of the maximum mutual information (MMI) objective function
which gives improved results for discriminative training. The modification consists of …
which gives improved results for discriminative training. The modification consists of …
Discriminative learning in sequential pattern recognition
In this article, we studied the objective functions of MMI, MCE, and MPE/MWE for
discriminative learning in sequential pattern recognition. We presented an approach that …
discriminative learning in sequential pattern recognition. We presented an approach that …
HMMs and related speech recognition technologies
S Young - Springer handbook of speech processing, 2008 - Springer
Almost all present-day continuous speech recognition (CSR) systems are based on hidden
Markov models (HMMs). Although the fundamentals of HMM-based CSR have been …
Markov models (HMMs). Although the fundamentals of HMM-based CSR have been …
Conditional random fields for integrating local discriminative classifiers
J Morris, E Fosler-Lussier - IEEE Transactions on Audio …, 2008 - ieeexplore.ieee.org
Conditional random fields (CRFs) are a statistical framework that has recently gained in
popularity in both the automatic speech recognition (ASR) and natural language processing …
popularity in both the automatic speech recognition (ASR) and natural language processing …
Improvements in hidden Markov model based Arabic OCR
R Prasad, S Saleem, M Kamali… - 2008 19th …, 2008 - ieeexplore.ieee.org
This paper describes recent advances in hidden Markov model (HMM) based OCR for
machine-printed arabic documents. A combination of script-independent and script-specific …
machine-printed arabic documents. A combination of script-independent and script-specific …
Modified MMI/MPE: A direct evaluation of the margin in speech recognition
In this paper we show how common speech recognition training criteria such as the
Minimum Phone Error criterion or the Maximum Mutual Information criterion can be …
Minimum Phone Error criterion or the Maximum Mutual Information criterion can be …
A one-pass real-time decoder using memory-efficient state network
This paper presents our developed decoder which adopts the idea of statically optimizing
part of the knowledge sources while handling the others dynamically. The lexicon, phonetic …
part of the knowledge sources while handling the others dynamically. The lexicon, phonetic …
MPE-based discriminative linear transforms for speaker adaptation
L Wang, PC Woodland - Computer Speech & Language, 2008 - Elsevier
In this paper, the use of discriminative linear transforms (DLT) is investigated to construct
speaker adaptive speech recognition systems, where a discriminative criterion rather than …
speaker adaptive speech recognition systems, where a discriminative criterion rather than …
[PDF][PDF] Phonetic query expansion for spoken document retrieval.
J Mamou, B Ramabhadran - INTERSPEECH, 2008 - isca-archive.org
We are interested in retrieving information from speech data using phonetic search. We
show improvement by expanding the query phonetically using a joint maximum entropy N …
show improvement by expanding the query phonetically using a joint maximum entropy N …