Convolutional and Deep Neural Networks based techniques for extracting the age-relevant features of the speaker

Abstract

With the advent of conversational voice recognition systems such as Alexa, SIRI, OK Google, etc., natural language conversational scheme including Chatbot and voice recognition systems are in new high and determining the age of a speaker is critical for setting the pertinent context. Age can be inferred from the speech signal by inferring various factors such as physical attributes of voice, linguistic attributes, frequency, speech rate, etc., This paper discusses on extracting the spectral features of speech such as Cepstral Coefficients, Spectral Decrease, Centroid, Flatness, Spectral Entropy,Jitter and Shimmer as inputs which would also helps in classifying speaker age through deep learning techniques.A novel approach is addressed along with the model for implementation using Deep Neural Network and Convolutional Neural Network for classifying the features using three different classifiers.The results obtained from the proposed system would outline the performance in speaker age recognition.