Springer Verlag, Lecture Notes in Computer Science, p. 173-180
DOI: 10.1007/978-3-540-39398-6_25
Full text: Download
One of the goals of the EMBASSI1 project is the creation of a speech interface between a user and a TV set or VCR. The interface should allow spontaneous speech recorded by microphones far away from the speaker. This paper describes experiments evaluating the robustness of a speech recognizer against reverberation. For this purpose a speech corpus was recorded with several different distortion types under real- life conditions. On these data the recognition results for reverberated signals using µ-law companded features were compared to an MFCC baseline system. Trained with clear speech, the word accuracy for the µ-law features on highly reverberated signals was 3 percent points better than the baseline result.