Digital Signal Processing Reference
In-Depth Information
sniffing and tracking, new and more robust acoustic front-end representations
and built-in speaker normalization for robust ASR, and our back-end dialog
navigation information retrieval sub-system connected to the WWW. Results
are presented in each sub-section with a discussion at the end of the chapter.
Keywords:
Automatic speech recognition, robustness, microphone array processing, multi-
modal, speech enhancement, environmental sniffing, PMVDR features, dialog,
mobile, route navigation, in-vehicle
1.
INTRODUCTION: HANDS-FREE SPEECH
RECOGNITION/DIALOG IN CARS
There has been significant interest in the development of effective dialog
systems in diverse environmental conditions. One application which has
received much attention is for hands-free dialog systems in cars to allow the
driver to stay focused on operating the vehicle while either speaking via
cellular communications, command and control of vehicle functions (i.e.,
adjust radio, temperature controls, etc.), or accessing information via wireless
connection (i.e., listening to voice mail, voice dialog for route navigation and
planning). Today, many web based voice portals exist for managing call
center and voice tasks. Also, a number of spoken document retrieval systems
are available for information access to recent broadcast news content
including SpeechBot by HP-Compaq)[30] and the SpeechFind for historical
digital library audio content (RSPG-CSLR, Univ. Colorado)[29]. Access to
audio content via wireless connections is desirable in both commercial
vehicle environments (i.e., obtaining information on weather, driving
conditions, business locations, etc.), points of interest and historical content
(i.e., obtaining audio recordings which provide a narrative of historical places
for vacations, etc.), as well as in military environments (i.e., information
access for coordinating peacekeeping groups, etc.).
This chapter presents our recent activity in the formulation of a new in-
vehicle interactive system for route planning and navigation. The system
employs a number of speech processing sub-systems previously developed for
the DARPA CU Communicator[1] (i.e., natural language parser, speech
recognition, confidence measurement, text-to-speech synthesis, dialog
manager, natural language generation, audio server). The proposed CU-Move
