EUROSPEECH 2003 - INTERSPEECH 2003
8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003

        

Far-Field ASR on Inexpensive Microphones

Laura Docio-Fernandez (1), David Gelbart (2), Nelson Morgan (2)

(1) Universidad de Vigo, Spain
(2) International Computer Science Institute, USA

For a connected digits speech recognition task, we have compared the performance of two inexpensive electret microphones with that of a single high quality PZM microphone. Recognition error rates were measured both with and without compensation techniques, where both single-channel and two-channel approaches were used. In all cases the task was recognition at a significant distance (2-6 feet) from the talker's mouth. The results suggest that the wide variability in characteristics among inexpensive electret microphones can be compensated for without explicit quality control, and that this is particularly effective when both single-channel and two-channel techniques are used. In particular, the resulting performance for the inexpensive microphones used together is essentially equivalent to the expensive microphone, and better than for either inexpensive microphone used alone.

Full Paper

Bibliographic reference.  Docio-Fernandez, Laura / Gelbart, David / Morgan, Nelson (2003): "Far-field ASR on inexpensive microphones", In EUROSPEECH-2003, 2141-2144.