Creation and Assessment of Korean Speech and Noise DB in Car Environment
Yong-Ju Lee (1), Bong-Wan Kim (2), Young-Il Kim (2), Dae-Lim Choi (2), Kwang-Hyun Lee (2), Yongnam Um (2)
(1) Department of Electrical, Electronic and Information Engineering, Wonkwang University, 344-2, Sinyong-dong, Iksan, Chonbuk, Korea; (2) Speech Information Technology & Industry Promotion Center, 344-2, Sinyong-dong, Iksan, Chonbuk, Korea
Researches into robust recognition in noise environment, especially in car environment, are being carried out actively in speech community. In this paper we introduce three types of corpora that SITEC (Speech Information Technology & Industry Promotion Center) has created for research into speech recognition in car noise environment. The first is the recordings of 900 Korean native speakers, distributed according to gender, age, and region, who uttered command words in car environment. The second is the collection of mixed noise in 3 models of cars by while setting up various noise patterns which can be obtained with the car engine on or off, at different driving speed, and in different road conditions with windows open or closed. The third is the recording of simulated speech by HATS (Head and Torso Simulator) in car environment with the internal and external noise factors added. These three types of recordings were all made through synchronized 7 channels and a separate hands-free channel fixed in a car. The creation and specifications of these corpora will be reported on in detail.
speech and noise DB, robust recognition, car environment