Automatic speech recognition is a field related to the interaction between user and machine using effective techniques. ASR is one of the very hot concepts in these days. A lot of researchers worked on different techniques to achieve the best accuracy for speech recognition. In previous research techniques used provides accuracy for a single utterance. Due to which for continuous utterance combination of the technique used in this research work which provides best accurate performance with less noisy interaction. For this research work, Mel Frequency Cepstrum Coefficient (MFCC) and Vector Quantization (VQ) techniques are used. These techniques provide easy speech processing with Mel-frequency scale which includes spacing of linear frequency less than 1000 Hz. Due to which MFCC provides high accuracy, less complexity and high performance with capturing main characteristics of speech. This approach provides efficient and more accurate results than other techniques for a continuous speech by minimizing the distortion created by noise. In this research work algorithms for each technique are represented. This research work presents best possible accuracy for continuous speech signal as compared to other feature extraction techniques.
The proposed algorithm is a hybrid approach to find a software component. The hybrid approach is a combination of various modules called data extraction, Fact and rules, Optimization with genetic algorithm, etc. all these modules process raw data and provide the output as a component for reuse on the basis of various priorities matrixes. Proposed approach uses priority vector for the processing of all entries and define priorities on the basis of availability of various data factors along with issues in the software component. The entire component derived through the raking process with the help of genetic algorithm for the final output. Proposed approach provides average accuracy 99% for detection of software components. Various other parameters are also compared with the existing developed algorithms which provide comparative study and enhancement of the proposed method.
A code smell detection and refactor is one of the very hot concepts in these days. A Lot of researcher worked on it to create an automatic bad smell detection and refactoring system. Main purpose behind the development of these type of systems is to create automatic for enhance the development quality of software systems. In the previous research the smell detection system perform detection on specific areas or specific language. Due to this companies needs to use more than one detector for software testing for large projects. The system is combination of various modules which can be developed in various languages. Our proposed method which is helpful their users to test their code and detect bad smell on more than one language. It acts as a bridge with some optimization techniques which provide highly accurate working for smell detection along with refactoring. Proposed approach uses optimization along with fact and rule programming to detect and refactor the bad smell from input programs. Various bad smells like long methods, dead code, lazy class, long class, etc. are used to check the quality of the code. The proposed approach is also working for Java, c++ and c#.net codes for the test all these bad smell and refactor c++ and Java code. The performance of the proposed approach is also better than other existing algorithms in terms of accuracy for detection and refactoring of bad smells. Some other challenges that the proposed approach faced to find the smells in the code also affect the performance. One of the main challenges is the way of writing code is different for everyone. So it's difficult to detect and refactor the thing on smell detection tool. Proposed approach used fact and rule processing for detection and eliminates unwanted entries with the help of the optimization process. The performance in terms of accuracy and FAR, FRR are stable and better for all the test cases in the comparison of existing methods and proposed approach.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.