V. Mitra, J. van Hout, W. Wang, C. Bartels, H. F. D. Vergyri, A. Alwan, A. Janin, J.H.L. Hansen, R.M. Stern, A. Sangwan and N. Morgan, “Fusion Strategies for Robust Speech Recognition and Keyword Spotting for Channel- and Noise-Degraded Speech,” in Proc. INTERSPEECH 2016, pp. 3683-3687, September 2016.
Recognizing speech under high levels of channel and/or noise degradation is challenging. Current state-of-the-art automatic speech recognition systems are sensitive to changing acoustic conditions, which can cause significant performance degradation. Noise-robust acoustic features can improve speech recognition performance under varying background conditions, where it is usually observed that robust modeling techniques and multiple system fusion can help to improve the performance even further. This work investigates a wide array of robust acoustic features that have been previously used to successfully improve speech recognition robustness. We use these features to train individual acoustic models, and we analyze their individual performance. We investigate and report results for simple feature combination, feature-map combination at the output of convolutional layers, and fusion of deep neural nets at the senone posterior level. We report results for speech recognition on a large-vocabulary, noise- and channel-degraded Levantine Arabic speech corpus distributed through the Defense Advance Research Projects Agency (DARPA) Robust Automatic Speech Transcription (RATS) program. In addition, we report keyword spotting results to demonstrate the effect of robust features and multiple levels of information fusion.