Speech recognition for an information kiosk

Abstract

In the context of the ESPRIT MASK project we face the problem of adapting a "state-of-the-art" laboratory speech recognizer for use in the real world with naive users. The speech recognizer is a softwareonly system that runs in real-time on a standard Risc processor. All aspects of the speech recognizer have been reconsidered from signal capture to adaptive acoustic models and language models. The resulting system includes such features as microphone selection, response cancellation, noise compensation, query rejection capability and decoding strategies for real-time recognition.

Revisiting “Hole in the Wall” Computing

“…Another early example, which has since been refined and evaluated in a later investigation, is the MASK Kiosk [14,21] -an advanced public service terminal with multimodal input and output capabilities (including speech input). The results showed that multimodality was more efficient than monomodality, indicating that a combination of speech and touch input was an advantageous solution for walk-up kiosks of this nature.…”

Automatic speech recognition and its application to information extraction

“…A prototype French/English service for the high speed trains between Paris and London is also under development. The system is based on the spoken language systems developed for the RailTel project [11] and the ESPRIT Mask project [12]. Compared to the RailTel system, the main advances in ARISE are in dialogue management, confidence measures, inclusion of optional spell mode for ci, ty/station names, and barge-in capability to allow more natural interaction between the user and the machine.…”

Speech Recognition Enhancement Using Beamforming and a Genetic Algorithm

“…Speech recognition system is widely used in automatic remote control such as logistics warehouse [1], intelligence home [2], banking systems [3] and interactive children books [4]. It is usually based on the hidden Markov model (HMM) chain and is trained to recognize the commands using a large database of speech signals [5].…”