Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Lucent Automatic Speech Recognition: A Speech Recognition Engine for Internet and Telephony Srvice Applications

Qiru Zhou (1), Sergey Kosenko (2)

(1) Dialogue Systems Research Department, (2) Lucent Speech Solutions, Bell Labs, Lucent Technologies, Murray Hill, NJ, USA

Based on Bell Labs speech recognition and understanding technology, we developed LASR3 (Lucent Automatic Speech Recognition, Version 3), a speaker independent, software-based continuous speech recognition engine. It is compatible with Microsoft Speech Application Programming Interface (MS SAPI). LASR3 provides support for desktop, telephony, and internet applications requiring speech recognition. It is a multilingual, scalable multi-channel speech recognition engine. LASR3 runs on 32-bit Microsoft Windows platforms. This paper discusses the LASR3 algorithms, features, and architecture design for scalable multi-channel speech recognition.

Full Paper

Bibliographic reference.  Zhou, Qiru / Kosenko, Sergey (2000): "Lucent automatic speech recognition: a speech recognition engine for internet and telephony srvice applications", In ICSLP-2000, vol.2, 947-950.