Noise robustness is one of the most challenging problem in automatic speech recognition. The goal of robust feature extraction is to improve the performance of speech recognition in adverse conditions. The mel-scaled frequency cepstral coefficients (MFCCs) derived from Fourier transform and filter bank analysis are perhaps the most widely used front-ends in state-of-the-art speech recognition systems. One of the major issues with the MFCCs is that they are very sensitive to additive noise. To improve the robustness of speech front-ends we introduce, in this paper, a new set of MFCC vector which is estimated through three steps. First, the relative higher order autocorrelation coefficients are extracted. Then magnitude spectrum of the resultant speech signal is estimated through the fast Fourier transform (FFT) and it is differentiated with respect to frequency. Finally, the differentiated magnitude spectrum is transformed into MFCC-like coefficients. These are called MFCCs extracted from Differentiated Relative Higher Order Autocorrelation Sequence Specrum (DRHOASS). Speech recognition experiments for various tasks indicate that the new feature vector is more robust than traditional mel-scaled frequency cepstral coefficients (MFCCs) in additive noise conditions.
Machine learning has revolutionised speech technologies for major world languages, but these technologies have generally not been available for the roughly 4,000 languages with populations of fewer than 10,000 speakers. This paper describes the development of Elpis, a pipeline which language documentation workers with minimal computational experience can use to build their own speech recognition models, resulting in models being built for 16 languages from the Asia-Pacific region. Elpis puts machine learning speech technologies within reach of people working with languages with scarce data, in a scalable way. This is impactful since it enables language communities to cross the digital divide, and speeds up language documentation. Complete automation of the process is not feasible for languages with small quantities of data and potentially large vocabularies. Hence our goal is not full automation, but rather to make a practical and effective workflow that integrates machine learning technologies.
Recent developments in information gathering procedures and the collection of big data over a period of time as a result of introducing high computing devices pose new challenges in sensor networks. Data prediction has emerged as a key area of research to reduce transmission cost acting as principle analytic tool. The transformation of huge amount of data into an equivalent reduced dataset and maintaining data accuracy and integrity is the prerequisite of any sensor network application. To overcome these challenges, a data prediction technique is suggested to reduce transmission of redundant data by developing a regression model on linear descriptors on continuous sensed data values. The proposed model addresses the basic issues involved in data aggregation. It uses a buffer based linear filter algorithm which compares all incoming values and establishes a correlation between them. The cluster head is accountable for predicting data values in the same time slot, calculates the deviation of data values, and propagates the predicted values to the sink.
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.