Pop Sound Detection and Suppression

When we look at a close-talking automatic speech recognition (ASR) situation, the speech output of the user can become a problem, when the distance to the microphone is too small. Pressure impulses from plosive speech sounds (e.g., /p/,/t/,/k/) can result in a distortion of the audio signal, which results in a decrease of speech recognition accuracy. Pressure gradient microphones are especially sensitive to pop sounds. To reduce the effects of this problem, we identify several points in the signal chain, where one can improve the situation. One possibility would be to detect pop sounds when they occur and use a different recording channel to mitigate the effects of the distortion caused by the pop sound.

Your Tasks

• Develop and implement an algorithm that detects pop sounds
• Develop and Implement an intelligent algorithm that switches to a different recording channel
• Evaluate the effectiveness for ASR a using a pop sound generator
• Documentation

Your Profile

• Motivation and interest in the topic
• Signal Processing
• Matlab

Contact

Martin Hagmüller (hagmueller@tugraz.at or 0316/873 4377)