This paper exposes at the beginning most of the problems encountered in the automatic speech recognition, namely the complexity of speech signal, and the diversity of process of signal processing.For this, a review of general concepts in signal processing is inspected; after it has been specifically addressed the extraction phase, in order to conduct a thorough review of existing extraction methods in this area.The next task is reserved to a list of existing extractor's combinations, and finally an extractor's recombination is developed, with the aim of reaching a full treatment with a considerable amount of extracted vectors acoustic, in order to develop the recognition rate of Arabic numerals.
We started this report with a description of the organs constituting the speaker recognition system (SRS), so we immediately went on to explore the types of speaker recognition and the difficulties cited at this level. Next, we carried out a review of the main approaches to combinations and hybridizations developed over the past ten years in the field of the automatic speech recognition (ASR), by carrying out an experimental and comparative study of such an approach.Thus, we summarized the advantages and disadvantages presented by these methods of extraction and classification of acoustic characteristics, and their contributions to ASR.We have developed an approach to estimate a relevant speaker verification system, using a combined extractor, and a hybrid classifier, which allowed us to build our system of recognition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.