Recently automatic speech recognition (ASR) systems achieve higher and higher accuracy rates. However, the score drops significantly, when the ASR system is being used with a non-native speaker of the language to be recognized, mainly because of specific pronunciation and accent features. A limited volume of labeled datasets containing samples of a non-native speech makes it difficult to train any new ASR systems targeted for non-native speakers. In our research, we tried tackling the problem of a non-native accent and its influence on the accuracy of ASR systems, using the style transfer methodology. We designed a pipeline for modifying the speech produced by a nonnative speaker, so that it resembles the native speech to a higher extent, i.e. a method for accent neutralization. Our methodology can be used as a wrapper for any existing ASR system, which reduces the necessity of training new speech recognizers, adapted for non-native speech. The modification can be thus performed on the fly, before passing the data forward to the speech recognition system itself.
In this paper we consider the problem of detecting and recognizing widgets in screenshots of computer programs’ graphical user interface (GUI). This problem is fundamental in business process automation. The solution we propose here is based on detecting GUI elements with Canny edge operator, and recognizing already detected GUI elements with classifiers: neural networks, random forests, XGBoost, and others.
The second generation sequencing techniques opened doors to further research on a world scale, because the cost of DNA sequencing dropped significantly. However, the second generation sequencing technology has some drawbacks, mainly short read length. In 2017 the new devices, that use real-time sequencing started to be available. This approach, called "the third-generation sequencing" achieve read length of 20kbp and error rate about 15%. As a consequence of this process new DNA assemblers were developed. In this article we propose an implementation of Overlap Graph-based de novo assembly algorithm for third-generation sequencing data. The proposed method involves graph algorithms and dynamic programming, optimized using a MinHash filter. The solution has been tested on both simulated and real data of bacteria obtained from Oxford Nanopore MinION sequencer. The algorithm is included in "OLC" module of the dnaasm de novo assembler. Dnaasm application provides command line interface as well as web browser-based client. Source code as well as a demo web application and a docker image are available at the dnaasm project web-page: http://dnaasm.sourceforge.net.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.