Contemporary speech/speaker recognition with speech from impaired vocal apparatus

Speech is the effective form of communication between human and its environment. Speech also has potential of being important mode of interaction with computer. This review paper deals with both speech and speaker recognition of persons with speech motor disorders. Normally speaker recognition consists of speaker verification and speaker identification. Speaker identification is the process of determining which registered speaker provides a given input sample. Speaker verification is the process of accepting or rejecting the identity claim of a speaker. On the other hand, the speech recognition system deals with the following challenges such as speech representation, feature extraction techniques, speech classifiers, databases and performance evaluation. Motor speech disorders are a class of speech disorder that disturbs the body´s natural ability to speak. These disturbances vary in their etiology based on the integrity and integration of cognitive, neuromuscular, and musculoskeletal activities. There are various types of speech disorders like Apraxia, Cluttering (similar to stuttering), Dyspraxia, Dysarthria, Dysprosody and so on. The main objective of this review paper is to summarize and compare the well known methods used in various stages of speech and speaker recognition system.