01462nam a2200133Ia 4500008004100000041001200041100001600053245009500069260004400164510099400208942000701202999001901209952010001228231221s9999    xx            000 0 und d  aEnglish  aVikas, S A. 0aSpeech processing and speech music discrimination using spiking neural networksbVinay, A.  cJan-May 2019bPES UniversityaBengaluru  aThe music and speech discrimination in an audio signal have many practical applications in the multimedia domain such as automated speech recognition and classification, radio broadcast monitoring. This task involves segmentation of audio samples and classification of each sample into speech or music. The objective of the current work is to investigate implementation of audio segmentation for speech and music discrimination using SNN (Spiking Neural Network). The current approach uses CNN (Convolutional Neural Network) with SNN for recognition and classification of music and speech bits in an audio file through spectrograms. The Spiking Neural Networks are a class of ANNs (Artificial Neural Network) that more closely resemble natural and biological neural network that work on STDP (Spike Timing Dependent Plasticity) rule. The proposed approach focuses on implementation of a model to process the dataset that comprises of audio files covering wide range of music and speech sam  cCD  c237122d237122  r2024-01-26 00:00:00l0pCD7249w2024-01-26yCD10407000aMLbMLd0000-00-00ECS/PGGRSF1V0