An HMM based speaker-independent continuous speech recognition system with experiments on the TIMIT database
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 333-336 vol.1
- https://doi.org/10.1109/icassp.1991.150344
Abstract
The authors recently designed and implemented a large-vocabulary, speaker-independent, continuous speech recognition system. The system is based on hidden Markov modeling (HMM) of phoneme-sized acoustic units using continuous mixture Gaussian densities. The main structure of the system is outlined with a focus on a method of generating mixture Gaussian density models through a merging procedure whose efficiency was recently improved significantly. The system has been evaluated on the TIMIT database on a task of vocabulary size 853 and various grammar perplexities. The word accuracies are 92.2%, 84.9%, and 60.1% for the test set perplexities of 25, 106, and 853 (no grammar), respectively.<>Keywords
This publication has 6 references indexed in Scilit:
- Perceptually based linear predictive analysis of speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Continuous speech recognition results of the BYBLOS system on the DARPA 1000-word resource management databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Acoustic modeling of subword units for speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An HMM based speaker-independent continuous speech recognition system with experiments on the TIMIT databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Spectral slope distance measures with linear prediction analysis for word recognition in noiseIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- Speaker-independent isolated word recognition using dynamic features of speech spectrumIEEE Transactions on Acoustics, Speech, and Signal Processing, 1986