Direct models for phoneme recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2002, Pages 89-92

  Likhododev, Anton ^a   Gao, Yuqing ^b  

^a Carnegie Mellon University   (United States)

^b IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DIRECT MODEL TRAINING; HIDDEN MARKOV MODELS; MAXIMUM ENTROPY MARKOV MODELS; PHONEME RECOGNITION; VITERBI ALGORITHM;

ALGORITHMS; DECODING; LEARNING SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; PROBABILITY DENSITY FUNCTION; PROBABILITY DISTRIBUTIONS; SPEECH ANALYSIS; STATE SPACE METHODS; STATISTICAL METHODS;

SPEECH RECOGNITION;

EID: 0036289830     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2002.5743661     Document Type: Article

References (8)

1. A maximum likelihood approach to continuous speech recognition
2. A maximum entropy approach to natural language processing
3. Inducing features of random fields
4. Maximal rank likelihood as an optimization function for speech recognition
5. Maximum entropy Markov models for information extraction and segmentation
6. A tutorial on hidden Markov models and selected applications in speech recognition
7. A simple introduction to maximum entropy models for natural language processing
8. Conditional random fields: Probabilistic models for segmenting and labeling sequence data