论文信息 - Detection of Dialogue in Movie Soundtrack for Speech Intelligibility Enhancement

Detection of Dialogue in Movie Soundtrack for Speech Intelligibility Enhancement

A method for detecting dialogue in 5.1 movie soundtrack based on interchannel spectral disparity is presented. The front channel signals (left, right, center) are analyzed in the frequency domain. The selected partials in the center channel signal, which yield high disparity with left and right channels, are detected as dialogue. Subsequently, the dialogue frequency components are boosted to achieve increased dialogue intelligibility. The techniques for reduction of artifacts in the processed signal are also introduced. Smoothing in the time domain and in the frequency domain is applied to reduce unpleasant artifacts. The results of objective tests are provided, which prove that increased dialogue intelligibility is achieved with the aid of the proposed algorithm. The algorithm is particularly applicable in mobile devices while listening in mobile conditions.

Kuba Łopatka

[1] Petros Maragos,et al. Audio-Assisted Movie Dialogue Detection , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[2] David Malah,et al. Speech enhancement using a minimum mean-square error log-spectral amplitude estimator , 1984, IEEE Trans. Acoust. Speech Signal Process..

[3] Ioannis Pitas,et al. A neural network approach to audio-assisted movie dialogue detection , 2007, Neurocomputing.

[4] Andrzej Czyzewski,et al. Novel 5.1 Downmix Algorithm with Improved Dialogue Intelligibility , 2013 .

[5] Ronald R. Yager. Exponential smoothing with credibility weighted observations , 2013, Inf. Sci..

[6] Olivier Cappé,et al. Elimination of the musical noise phenomenon with the Ephraim and Malah noise suppressor , 1994, IEEE Trans. Speech Audio Process..

[7] Terrence J. Sejnowski,et al. Blind source separation of more sources than mixtures using overcomplete representations , 1999, IEEE Signal Processing Letters.

[8] Dan Barry,et al. Real-time Sound Source Separation: Azimuth Discrimination and Resynthesis , 2004 .

[9] Ching-Wei Chen,et al. Improving melody extraction using Probabilistic Latent Component Analysis , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10] Kah-Chye Tan,et al. Postprocessing method for suppressing musical noise generated by spectral subtraction , 1998, IEEE Trans. Speech Audio Process..