- Abstract:
-
The analysis of scenarios in which a number of microphones record the activity of speakers, such as
in a roundtable meeting, presents a number of computational challenges. For example, if each participant wears a microphone, it can receive speech from both the microphone's wearer (local speech) and from other participants (crosstalk). The
recorded audio can be broadly classified in four ways: local speech, crosstalk plus local speech, crosstalk alone and silence. We describe two experiments related to the automatic classification of audio into these four classes. The first experiment attempted to optimise a set of acoustic features for use with a Gaussian mixture model (GMM)
classifier. A large set of potential acoustic features were considered, some of which have been employed in previous studies. The best-performing features were found to be kurtosis, fundamentalness
and cross-correlation metrics. The second experiment
used these features to train an ergodic hidden Markov model classifier. Tests performed on a large corpus of recorded meetings show classification accuracies of up to 96\%, and automatic speech recognition performance close to that obtained using
ground truth segmentation.
- Links To Paper
- 1st Link
- 2nd Link
- Bibtex format
- @Article{EDI-INF-RR-0661,
- author = {
S. J. Wrigley
and G J Brown
and V Wan
and Steve Renals
},
- title = {Speech and crosstalk detection in multi-channel audio},
- journal = {IEEE Transactions on Speech and Audio Processing},
- publisher = {IEEE Signal Processing Society},
- year = 2005,
- month = {Jan},
- volume = {# 13(1)},
- pages = {84-91},
- doi = {10.1109/TSA.2004.838531},
- url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=29967&arnumber=1369314&count=12&index=7},
- }
|