ST outs MEMS microphone for voice-enabled homes

The DIRHA project sets to address the challenge of distant speech interaction in multinoise, multispeaker situations of a home environment. The goal is to create a pervasive, always-listening sound space, where users needn't speak into the microphone to get recognized and understood, but the system reaches out, acoustically, to the speakers regardless of their position within the home.

The physical and acoustic parameters of ST's MEMS microphones perfectly fit the challenging requirements of distant-speech interaction systems, said the company. The small form factor allows the researchers to easily embed entire arrays of microphones in the walls, desks, or speech-enabled appliances of the automated home, while the microphones' excellent acoustic characteristics, coupled with sophisticated signal-processing technologies, will make it possible to identify and capture an individual speaker from several meters away, in a crowded room with music playing.

The distant-speech interaction capability will not only dramatically change the way people interact with technology, but can make a real difference for those who can't easily move around, such as the elderly or the motor-impaired. In addition to the home scenarios, the distant-speech interaction systems can find use in robotics, telepresence, surveillance and industry automation.

The main fields of research include multichannel acoustic processing, distant-speech recognition and understanding, speaker identification/verification, and spoken-dialog management in four languages—German, Greek, Italian and Portuguese. The final prototypes will be integrated in pilot households and evaluated by real users.