An Overview of the Philips Research System for Large Vocabulary Continuous Speech Recognition

H. Ney, V. Steinbeiss, R. Haeb-Umbach, B.H. Tran, International Journal on Pattern Recognition and Artificial Intelligence (1994).

Download
No fulltext has been uploaded.
Journal Article | English
Author
Ney, Hermann; Steinbeiss, Volker; Haeb-Umbach, ReinholdLibreCat; Tran, Bach Hiep
Abstract
This paper gives an overview of a research system for phoneme based, large vocabulary continuous speech recognition. The system to be described has been applied to the SPICOS task, the DARPA RM task and a 12000 word dictation task. Experimental results for these three tasks will be presented. Like many other systems, the recognition architecture is based on an integrated statistical approach. In this paper, we describe the characteristic features of the system as opposed to other systems: (1) The Viterbi criterion is consistently applied both in training and testing. (2) Continuous mixture densities are used without any tying or smoothing; this approach can be viewed as a sort of ‘statistical template matching’. (3) Time-synchronous beam search is used consistently throughout all tasks; extensions using a tree organization of the vocabulary and phoneme lookahead are presented so that a 12000 word task can be handled.
Publishing Year
Journal Title
International Journal on Pattern Recognition and Artificial Intelligence
LibreCat-ID

Cite this

Ney H, Steinbeiss V, Haeb-Umbach R, Tran BH. An Overview of the Philips Research System for Large Vocabulary Continuous Speech Recognition. International Journal on Pattern Recognition and Artificial Intelligence. 1994.
Ney, H., Steinbeiss, V., Haeb-Umbach, R., & Tran, B. H. (1994). An Overview of the Philips Research System for Large Vocabulary Continuous Speech Recognition. International Journal on Pattern Recognition and Artificial Intelligence.
@article{Ney_Steinbeiss_Haeb-Umbach_Tran_1994, title={An Overview of the Philips Research System for Large Vocabulary Continuous Speech Recognition}, journal={International Journal on Pattern Recognition and Artificial Intelligence}, author={Ney, Hermann and Steinbeiss, Volker and Haeb-Umbach, Reinhold and Tran, Bach Hiep}, year={1994} }
Ney, Hermann, Volker Steinbeiss, Reinhold Haeb-Umbach, and Bach Hiep Tran. “An Overview of the Philips Research System for Large Vocabulary Continuous Speech Recognition.” International Journal on Pattern Recognition and Artificial Intelligence, 1994.
H. Ney, V. Steinbeiss, R. Haeb-Umbach, and B. H. Tran, “An Overview of the Philips Research System for Large Vocabulary Continuous Speech Recognition,” International Journal on Pattern Recognition and Artificial Intelligence, 1994.
Ney, Hermann, et al. “An Overview of the Philips Research System for Large Vocabulary Continuous Speech Recognition.” International Journal on Pattern Recognition and Artificial Intelligence, 1994.

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar