DSP in Cell phones
Abstract: This paper describes a proposed algorithm for speech/music discrimination, which works on data directly taken from MPEG encoded bitstream thus avoiding the computationally difficult decoding-encoding process. The method is based on thresholding of features derived from the modulation envelope of the frequency-limited audio signal. The discriminator is tested on more than 2 hours of audio data, which contain clean and noisy speech from several speakers and a variety of music content. The discriminator is able to work in real time and despite its simplicity, results are very promising. Key-Words: audio, video, classification, speech, music, signal processing, MPEG 1 Introduction The work described in this paper under the auspices of the Centre for Digital Video Processing (CDVP) in cooperation with the Research Institute for Networks and Communications Engineering (RINCE) at Dublin City University. The CDVP research work concentrates on digital video analysis and multimedia content management.