Training of across-word phoneme models for large vocabulary continuous speech recognition

Achim Sixtus; Hermann Ney

doi:10.1109/icassp.2002.5743872

ScienceGate Book Chapters

JOURNAL ARTICLE

Training of across-word phoneme models for large vocabulary continuous speech recognition

Achim Sixtus Hermann Ney

Year: 2002 Journal: IEEE International Conference on Acoustics Speech and Signal Processing Vol: 3 Pages: I-849

DOI: 10.1109/icassp.2002.5743872

Get Full-Text PDF Get Analytical Report

Abstract

Today's speech recognition systems use across-word context dependent phoneme models to capture coarticulation across word boundaries. While there are several publications about the organization of across-word model search, there are hardly any descriptions about the training of across-word models.

Keywords:

Coarticulation Computer science Word (group theory) Vocabulary Speech recognition Natural language processing Context (archaeology) Artificial intelligence Word error rate Word recognition Linguistics

Metrics

Cited By

0.31

FWCI (Field Weighted Citation Impact)

Refs

0.53

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Topics

Speech Recognition and Synthesis

Physical Sciences → Computer Science → Artificial Intelligence

Natural Language Processing Techniques

Physical Sciences → Computer Science → Artificial Intelligence

Topic Modeling

Physical Sciences → Computer Science → Artificial Intelligence

Training of across-word phoneme models for large vocabulary continuous speech recognition

Abstract

Metrics

Topics

Related Documents

Training of across-word phoneme models for large vocabulary continuous speech recognition

Multonic Markov word models for large vocabulary continuous speech recognition

Robust Acoustic Model Training Against Phoneme Variations for Large Vocabulary Continuous Speech Recognition

Robust Acoustic Model Training Against Phoneme Variations for Large Vocabulary Continuous Speech Recognition

Adaptable phoneme-based models for large-vocabulary speech recognition