The modifications and improvements of the acoustic recognition component of the SPICOS system for the DARPA naval resource management task are described. These modifications and improvements include: the modeling of the continuous mixture densities of the acoustic vectors, the choice of suitable context-dependent phoneme units and the construction of generalized context phoneme units, and the modeling of transitional information in the acoustic vector. The experimental results show that critical factors are the acoustic resolution of the probability distributions and the context information captured in the acoustic vectors. By these enhancements, the system was able to attain a word error rate of 23.6% and 26.5% on two test sets in speaker-independent recognition mode, when trained on 80 speakers. The word pair grammar reduced the word error rate to 7.1% and 9.3% respectively.
Experiments on mixture-density phoneme-modelling for the speaker-independent 1000-word speech recognition DARPA task
Experimente für eine Ansatz-verteilte Lautmodellierung für die Sprecher-unabhängige 1000-Wort Spracherkennung DARP
1990
4 Seiten, 9 Quellen
Aufsatz (Konferenz)
Englisch
Mathematical Analysis and Speaker-Independent Speech Recognition
British Library Online Contents | 1996
|The DARPA PerceptOR evaluation experiments
British Library Online Contents | 2007
|Air Traffic Control Speech Recognition System Cross-Task & Speaker Adaptation
Online Contents | 2006
|An Improved HMM/VQ Training Procedure for Speaker-Independent Isolated Word Recognition
British Library Conference Proceedings | 1994
|