Title :
Better speech recognition accuracy in noisy environments using voice extraction
Author :
Zuluaga, Walter ; Amalashekaran, Karthikeyan ; Chisholm, Jeff
Author_Institution :
Clarity LLC, Auburn Hills, MI, USA
Abstract :
Results for voice extraction techniques embedded in Clarity´s Clear Voice Capture (CVC) are presented, showing an important increase in voice quality and speech recognition performance, when speech is registered in highly noisy environments. Controlled and field tests were performed in a variety of environments, e.g., anechoic rooms, restaurants and automobiles with large and small vocabulary speech recognition packages. The resulting recognition accuracy is compared with common directional microphones and array microphones
Keywords :
acoustic noise; anechoic chambers (acoustic); speech recognition; vocabulary; Clarity; Clear Voice Capture; anechoic rooms; automobiles; field tests; noisy environments; restaurants; speech recognition accuracy; vocabulary; voice extraction; voice quality; Acoustic noise; Circuit noise; Circuit testing; Microphones; Noise cancellation; Signal processing; Signal to noise ratio; Speech recognition; Vocabulary; Working environment noise;
Conference_Titel :
Circuits and Systems, 2000. Proceedings of the 43rd IEEE Midwest Symposium on
Conference_Location :
Lansing, MI
Print_ISBN :
0-7803-6475-9
DOI :
10.1109/MWSCAS.2000.952827