Readings in Speech Recognition

Readings in Speech Recognition

Author: Alexander Waibel

Publisher: Morgan Kaufmann

Published: 1990-05

Total Pages: 664

ISBN-13: 9781558601246

DOWNLOAD EBOOK

Speech recognition by machine : a review / D.R. Reddy -- The value of speech recognition systems / W.A. Lea -- Digital representations of speech signals / R.W. Schafer and L.R. Rabiner -- Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences / S.B. Davis and P. Mermelstein -- Vector quantization / R.M. Gray -- A joint synchrony-mean-rate model of auditory speech processing / S. Seneff -- Isolated and connected word recognition : theory and selected applications / L.R. Rabiner and S.E. Levinson -- Minimum prediction residual principle applied to speech recognition / F. Itakura -- Dynamic programming algorithm optimization for spoken word recognition / S. Hakoe and S. Chiba -- Speaker-independent recognition of isolated words using clustering techniques / L.R. Rabiner [and others]Two-level DP-matching : a dynamic programming-based pattern matching algorithm for connected word recognition / H. Sakoe -- The use of a one-stage dynamic pr ...


Information Systems Design and Intelligent Applications

Information Systems Design and Intelligent Applications

Author: Suresh Chandra Satapathy

Publisher: Springer

Published: 2016-02-03

Total Pages: 649

ISBN-13: 8132227573

DOWNLOAD EBOOK

The third international conference on INformation Systems Design and Intelligent Applications (INDIA – 2016) held in Visakhapatnam, India during January 8-9, 2016. The book covers all aspects of information system design, computer science and technology, general sciences, and educational research. Upon a double blind review process, a number of high quality papers are selected and collected in the book, which is composed of three different volumes, and covers a variety of topics, including natural language processing, artificial intelligence, security and privacy, communications, wireless and sensor networks, microelectronics, circuit and systems, machine learning, soft computing, mobile computing and applications, cloud computing, software engineering, graphics and image processing, rural engineering, e-commerce, e-governance, business computing, molecular computing, nano-computing, chemical computing, intelligent computing for GIS and remote sensing, bio-informatics and bio-computing. These fields are not only limited to computer researchers but also include mathematics, chemistry, biology, bio-chemistry, engineering, statistics, and all others in which computer techniques may assist.


Innovations in Information and Communication Technologies (IICT-2020)

Innovations in Information and Communication Technologies (IICT-2020)

Author: Pradeep Kumar Singh

Publisher: Springer Nature

Published: 2021-07-15

Total Pages: 474

ISBN-13: 3030662187

DOWNLOAD EBOOK

This edited book is comprised of original research that focuses on technological advancements for effective teaching with an emphasis on learning outcomes, ICT trends in higher education, sustainable developments and digital ecosystem in education, management and industries. The contents of the book are classified as; (i) Emerging ICT Trends in Education, Management and Innovations (ii) Digital Technologies for advancements in education, management and IT (iii) Emerging Technologies for Industries and Education, and (iv) ICT Technologies for Intelligent Applications. The book represents a useful tool for academics, researchers, industry professionals and policymakers to share and learn about the latest teaching and learning practices supported by ICT. It also covers innovative concepts applied in education, management and industries using ICT tools.


Speech Recognition Using Neural Nets and Dynamic Time Warping

Speech Recognition Using Neural Nets and Dynamic Time Warping

Author: Gary D. Barmore

Publisher:

Published: 1988

Total Pages: 291

ISBN-13:

DOWNLOAD EBOOK

The purpose of this study is to demonstrate the feasibility of using Kohonen neural nets in speech recognition. This is done by combining a first level Kohonen net with a work recognition algorithm which is either dynamic time warping (DTW) or a second Kohonen net. A digitized utterance is sliced and processed to obtain a sequence of 15 component vectors. Each component corresponds to the energy in a selected frequency range. An utterance of the digits zero through nine is used to train the first Kohonen net. After training, an utterance input to the net produces a trajectory through the net. Each point on the trajectory corresponds to a node and a particular sound. These trajectories are input to a work recognition algorithm. The first of these, DTW, compares unknown utterances to template utterances. It is a computationally intense, mathematical algorithm, and it was used primarily to test the preprocessing and neural net training procedures. The second algorithm is a second Kohonen neural net. Digits are assigned to each node so that when an unknown trajectory is input to the second net, the node that lights up identifies the utterance. Using DTW, 99% isolated and 93% connected speech recognition rates are achieved. With the second Kohonen net, isolated speech is recognized at up to 96%, depending upon the net format. Recommendations for future effort include increasing the vocabulary, using multiple feature sets and nets to attempt speaker independent speech recognition, and substituting a backward propagation multi-layer perceptron net for word recognition. Theses. (RH).