Automation of alternate billed calls using speech recognition

1 January 1991

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Magazine

Vol. 29 (1) , 25-29
https://doi.org/10.1109/35.64720

Abstract

Alternate billed calls (collect, calling-card, bill-to-third-party), which represent close to 50% of the toll and assist traffic in North America, requiring substantial operator workforce expenditures for telephone companies, are addressed. The automated alternate billing service (AABS), which automates a large component of this traffic, is described. Emphasis is on the use of advances in voice recognition technology and an innovative call script tool designed to simplify realization of the AABS application. Network interfaces, voice-processing hardware, speech recognition, call processing, fraud, bilingual support, and future enhancements are discussed.

Keywords

This publication has 4 references indexed in Scilit:

Decision rules for speaker-independent isolated word recognition
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2005
A linear predictive HMM for vector-valued observations with applications to speech recognition
IEEE Transactions on Acoustics, Speech, and Signal Processing, 1990
Use of vowel duration information in a large vocabulary word recognizer
The Journal of the Acoustical Society of America, 1989
Fast search strategy in a large vocabulary word recognizer
The Journal of the Acoustical Society of America, 1988