Context-dependent acoustic modeling using graphemes for large vocabulary speech recognition

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

Volumn 1, Issue , 2002, Pages

  Kanthak, S ^a   Ney, H ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

GRAPHEMES; LARGE VOCABULARY SPEECH RECOGNITION; PHONEMIC ACOUSTIC MODELS; WORD ERROR RATE;

COMPUTER SIMULATION; LINGUISTICS; MARKOV PROCESSES; OPTIMIZATION; STATISTICAL METHODS;

SPEECH RECOGNITION;

EID: 0036295940     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Continuous parameter acoustic processing for recognition of a natural speech corpus
2. Automatic speech recognition without phonemes
3. Experiments in syllable-based recognition of continuous speech
4. Improved hidden markow modelling of phonemes for continuous speech recognition
5. An efficient way to learn english grapheme-to-phoneme rules automatically
6. Heuristical and statistical methods for grapheme-to-phoneme conversion
7. Grapheme based speech recognition for large vocabularies
8. Decision tree based text-to-phoneme mapping for speech recognition
9. Information theoretic approach to the automatic determination of phonemic baseforms
10. Automatic generation of phone sets and lexical transcriptions
11. State tying for context dependent phoneme models
12. Automatic question generation for decision tree based state tying
13. The rwth large vocabulary continuous speech recognition system