A novel VQ-based speech recognition approach for mobile terminals

Xing He, Michael Scordilis, Gongjun Li

Research output: Contribution to journalConference article

Abstract

The ability to deploy speech recognition in mobile terminals, such as cell phones, has been limited to simple tasks due to restricted computational power and available memory. In this paper we present a new acoustic model based on vector quantization (VQ), which is better-suited for the limitations of the mobile environment. The proposed model is contrasted against finite state vector quantization (FSVQ); a commonly used technique is such environments. Performance enhancements include, temporal restrictions to state generation, a flexible number of vectors per state, and updates of the traditional state transition function to a higher order. Experimental results show that the new model improves the recognition rate and reduces the computation load.

Original languageEnglish (US)
Pages (from-to)433-436
Number of pages4
JournalConference Proceedings - IEEE SOUTHEASTCON
StatePublished - Nov 9 2005
EventIEEE Southeastcon 2005: Excellence in Engineering, Science and Technology - Ft. Lauderdale, United Kingdom
Duration: Apr 8 2005Apr 10 2005

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'A novel VQ-based speech recognition approach for mobile terminals'. Together they form a unique fingerprint.

  • Cite this