Speech Processing

Speech creation mechanism modeling: Speech creation mechanism, speech sounds. Digital speech preprocessing: Sampling rate, Digitisation, short term analysis, window size and rate of movement. Acoustic parameters: feature extraction, acoustic features for speaker differentiation, signal energy and zero crossing rate, fundamental frequency, FORMANTS, LPC, Cepstral coefficients. Speech to text systems. Speech synthesis. Noise removal methods. Music representation, musical feature extraction, legal issues of music information research, musical information retrieval and data mining. Bibliography:

Objectives

Speech creation mechanism modeling: Speech creation mechanism, speech sounds. Digital speech preprocessing

Prerequisites

Non required

Syllabus

Speech creation mechanism modeling: Speech creation mechanism, speech sounds. Digital speech preprocessing: Sampling rate, Digitisation, short term analysis, window size and rate of movement. Acoustic parameters: feature extraction, acoustic features for speaker differentiation, signal energy and zero crossing rate, fundamental frequency, FORMANTS, LPC, Cepstral coefficients. Speech to text systems. Speech synthesis. Noise removal methods. Music representation, musical feature extraction, legal issues of music information research, musical information retrieval and data mining. Bibliography: