TUT Acoustic Event Detection System 2007
This paper describes a system used in acoustic event detection task of the CLEAR 2007 evaluation. The objective of the task is to detect acoustic events (door slam, steps, paper wrapping etc.) using acoustic data from a multiple microphone set up in the meeting room environment. A system based on hidden Markov models and multi-channel audio data was implemented. Mel-Frequency Cepstral Coefficients are used to represent the power spectrum of the acoustic signal. Fully-connected three-state hidden Markov models are trained for 12 acoustic events and one-state models are trained for speech, silence, and unknown events.
KeywordsHide Markov Model Acoustic Event Meeting Room Reference Event Observation Probability
Unable to display preview. Download preview PDF.
- 5.Rabiner, L., Juang, B.H.: Fundamentals of Speech Recognition. PTR Prentice-Hall Inc, New Jersey (1993)Google Scholar
- 6.CLEAR: AED Evaluation Plan (2007), http://isl.ira.uka.de/clear07/download=CLEAR_2007_AED_EvaluationPlan.pdf
- 7.NIST: Spring (RT-05S) Rich Transcription Meeting Recognition Evaluation Plan (2005), http://nist.gov/speech/tests/rt/rt2005/spring/rt05smeetingeval-plan-V1.pdf