Acoustic Speech Recognition

Computer Engineering

Speech recognition is a process of recognition of human speech by computer producing string output of spoken sentence in written form. A model is learned from a set of audio recordings whose corresponding transcripts are created by taking audio recordings of speech and their text transcriptions, and using software to create statistical representations of the sound that make up every word. Speech based applications are getting enormous popularity by incorporating Natural Language Processing(NLP) techniques. Input to such applications is in natural language and output is obtained in natural language. In case of speech recognition system, research followers are mostly using three different methods namely Acoustic phonetic method, Pattern recognition approach and Artificial intelligence method. ASR today finds widespread application in tasks that require human machine interfaces. This paper presents a review on various existing techniques employed in building ASR models. Keywords— Automatic Speech Recognition system(ASR) , ASR classification, Speech Analysis, Feature extraction, Modelling techniques, Acoustic- Phonetic approach, Pattern Recognition methods, A.I approach, Language Modelling, ASR tools.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.