Non-intrusive bit-rate detection of coded speech. Sharma, D., Jost, U., & Naylor, P. A. In 2017 25th European Signal Processing Conference (EUSIPCO), pages 1799-1803, Aug, 2017.
Non-intrusive bit-rate detection of coded speech [pdf]Paper  doi  abstract   bibtex   
We present a non-intrusive codec type and bit-rate detection algorithm that extracts a number of features from a decoded speech signal and models their statistics using a Deep Neural Network (DNN) classifier. We also present a method for reducing the computational complexity and improving the robustness of the algorithm by pruning features that have a low importance and high computational cost using a CART binary tree. The proposed method is tested on a database that includes additive noise and transcoding as well as a real voicemail database. We show that the proposed method has 25% lower complexity than the baseline, 19% higher accuracy in the bitrate detection task and 10% higher accuracy in the CODEC classification experiment.

Downloads: 0