CONF Korchagin_ICASSP_2010/IDIAP Automatic Temporal Alignment of AV Data with Confidence Estimation Korchagin, Danil Garner, Philip N. Dines, John pattern matching reliability estimation time synchronization time-frequency analysis EXTERNAL http://publications.idiap.ch/attachments/papers/2009/Korchagin_ICASSP_2010.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/Korchagin_Idiap-RR-40-2009 Related documents Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing Dallas, USA 2010 P.O. Box 592, CH-1920 Martigny, Switzerland March 2010 In this paper, we propose a new approach for the automatic audio-based temporal alignment with confidence estimation of audio-visual data, recorded by different cameras, camcorders or mobile phones during social events. All recorded data is temporally aligned based on ASR-related features with a common master track, recorded by a reference camera, and the corresponding confidence of alignment is estimated. The core of the algorithm is based on perceptual time-frequency analysis with a precision of 10 ms. The results show correct alignment in 99% of cases for a real life dataset and surpass the performance of cross correlation while keeping lower system requirements. REPORT Korchagin_Idiap-RR-40-2009/IDIAP Automatic Temporal Alignment of AV Data with Confidence Estimation Korchagin, Danil Garner, Philip N. Dines, John pattern matching reliability estimation time synchronisation time-frequency analysis EXTERNAL http://publications.idiap.ch/attachments/reports/2009/Korchagin_Idiap-RR-40-2009.pdf PUBLIC Idiap-RR-40-2009 2009 Idiap CH-1920 Martigny, Switzerland December 2009 In this paper, we propose a new approach for the automatic audio-based temporal alignment with confidence estimation of audio-visual data, recorded by different cameras, camcorders or mobile phones during social events. All recorded data is temporally aligned based on ASR-related features with a common master track, recorded by a reference camera, and the corresponding confidence of alignment is estimated. The core of the algorithm is based on perceptual time-frequency analysis with a precision of 10 ms. The results show correct alignment in 99% of cases for a real life dataset and surpass the performance of cross correlation while keeping lower system requirements.