Filters








2,269 Hits in 7.4 sec

Exploration of Speech enabled System for English [article]

Kamlesh Sharma, T. Suryakanthi, T. V. Prasad
2013 arXiv   pre-print
There are large number of companies who are working in these area and developing software for the people who are not able to control the system through keyboard or mouse such as physically impaired and  ...  Windows speech recognition have many innovative features for Windows operating system and efficiently assist the computer to control, dictate, navigate, selecting the words, sending emails and correcting  ...  , two-pass large vocabulary continuous speech recognition (LVCSR) decoder software for speech which can perform almost real-time decoding on most current PCs in 60k word dictation task using word 3-  ... 
arXiv:1304.8013v1 fatcat:z4p3uzdw7jfwlmji2u2k5iyyxa

Converting the Point of View of Messages Spoken to Virtual Assistants [article]

Isabelle G. Lee, Vera Zu, Sai Srujana Buddi, Dennis Liang, Jack G.M. Fitzgerald
2020 arXiv   pre-print
We designed a system to allow virtual assistants to take a voice message from one user, convert the point of view of the message, and then deliver the result to its target user.  ...  GPT) for naturalness.  ...  The model consists of 256-dimensional word embeddings, a Long Short Term Memory (LSTM) encoder, dot product attention, a hidden representation of 256 dimensions, and an LSTM decoder.  ... 
arXiv:2010.02600v2 fatcat:z56gbmcmsrc3fkl7prxwbibce4

A multiplatform speech recognition decoder based on weighted finite-state transducers

Emilian Stoimenov, Tanja Schultz
2009 2009 IEEE Workshop on Automatic Speech Recognition & Understanding  
After describing the design, the network construction and storage process, we present evaluation results on a small task suitable for embedded applications, and on a large task, namely the European Parliament  ...  The reduced search effort makes static graph decoders an attractive alternative for tasks concerned with limited processing power or memory footprint on devices such as PDAs, internet tablets, and smart  ...  ACKNOWLEDGEMENTS The authors wish to thank Thilo Köhler and Christian Fügen for providing the BTEC system and their active support.  ... 
doi:10.1109/asru.2009.5373404 dblp:conf/asru/StoimenovS09 fatcat:owfpsokcpvatxdeawihqrwgorq

Automatic recognition and understanding of spoken language - a first step toward natural human-machine communication

Bing-Hwang Juang, S. Furui
2000 Proceedings of the IEEE  
Today, research results in spoken language processing have led to a number of successful applications, ranging from dictation software for personal computers and telephone-call processing systems for automatic  ...  The promise of a powerful computing device to help people in productivity as well as in recreation can only be realized with proper human-machine communication.  ...  As discussed previously, for large-vocabulary continuous speech recognition, composite models comprising sequences of unitary models are used for "pattern matching."  ... 
doi:10.1109/5.880077 fatcat:6ca4ebtwcbg4tl6bgcvgtr2gry

Distributed speech processing in miPad's multimodal user interface

Li Deng, Kuansan Wang, A. Acero, Hsiao-Wuen Hon, J. Droppo, C. Boulis, Ye-Yi Wang, D. Jacoby, M. Mahajan, C. Chelba, X.D. Huang
2002 IEEE Transactions on Speech and Audio Processing  
In a typical scenario, the user speaks to the device at a distance so that he or she can see the screen.  ...  It fully integrates continuous speech recognition and spoken language understanding, and provides a novel solution for data entry in PDAs or smart phones, often done by pecking with tiny styluses or typing  ...  He was general co-chair of the 2001 IEEE Workshop on Automatic Speech Recognition and Understanding, sponsorship chair of the 1999 IEEE Workshop on Automatic Speech Recognition and Understanding, and publications  ... 
doi:10.1109/tsa.2002.804538 fatcat:dwqnlnzaafbkrhhpqey5znonk4

Speech and language processing for next-millennium communications services

R.V. Cox, C.A. Kamm, L.R. Rabiner, J. Schroeter, J.G. Wilpon
2000 Proceedings of the IEEE  
., voice, video, music, etc.) and data into a single network, with ubiquitous access to that network anywhere, anytime, and by a wide range of devices.  ...  synthesis, recognition, and understanding for dialogue access to information, people, and messaging; and speaker verification for secure access to information and services.  ...  The conceptual HMM used in the decoder is trained on a large sample of sentences that were segmented by hand into concepts.  ... 
doi:10.1109/5.880086 fatcat:pzd6bawvirfo7c64t4zou2h4hy

Spoken Language Interface for Mobile Devices [chapter]

João Freitas, António Calado, Maria João Barros, Miguel Sales Dias
2009 Lecture Notes in Computer Science  
Voice Command is a product designed for Pocket PC and Smartphone devices that allows the user to command and control the device using his voice.  ...  The success of a speech application in mobile devices is dependent on a series of aspects related with the nature of the task such as usage scenarios, type of user application performance, required memory  ...  Maria João Barros for her excellent orientation, help and availability throughout this work.  ... 
doi:10.1007/978-3-642-04235-5_3 fatcat:lpmrafr6wza5zm4umbizvgsw34

Domain and Speaker Adaptation for Cortana Speech Recognition

Yong Zhao, Jinyu Li, Shixiong Zhang, Liping Chen, Yifan Gong
2018 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Voice assistant represents one of the most popular and important scenarios for speech recognition.  ...  Second, we directly update the existing model parameters for domain adaptation.  ...  INTRODUCTION The application of deep neural networks (DNNs) [1, 2, 3, 4] and recurrent neural networks (RNNs) [5, 6, 7, 8] has achieved tremendous success for large vocabulary continuous speech recognition  ... 
doi:10.1109/icassp.2018.8461553 dblp:conf/icassp/ZhaoLZCG18 fatcat:mirgz2h47fgolmgsyox3eoioju

Fast and Precise Touch-Based Text Entry for Head-Mounted Augmented Reality with Variable Occlusion

John J. Dudley, Keith Vertanen, Per Ola Kristensson
2018 ACM Transactions on Computer-Human Interaction  
Our system uses a statistical decoder to infer users' intended text and to provide error-tolerant predictions.  ...  Users select keys on the virtual keyboard by imitating the process of single-hand typing on a physical touchscreen display.  ...  As described in Section 4.1, the decoder incorporated a vocabulary of 64,000 words. The out of vocabulary percentage for the Experiment 1 phrase set was 0.56%.  ... 
doi:10.1145/3232163 fatcat:vivek5bwjbarba5f73wigoot7m

A system for spoken query information retrieval on mobile devices

E. Chang, F. Seide, H.M. Meng, Zhuoran Chen, Yu Shi, Yuk-Chi Li
2002 IEEE Transactions on Speech and Audio Processing  
This paper presents a system that allows the user to search for information on mobile devices using spoken natural-language queries.  ...  With the proliferation of handheld devices, information access on mobile devices is a topic of growing relevance.  ...  Li for their contributions. We would also like to thank Dr. J. Gao and Dr. M. Zhou for providing the TREC Chinese database and many useful suggestions.  ... 
doi:10.1109/tsa.2002.804301 fatcat:izcyym2axnbk5fpo5tbq5vd6qq

Vulnerability Analysis of the Android Kernel [article]

Joseph R. Barr, Peter Shaw, Tyler Thatcher
2021 arXiv   pre-print
The workflow represents a novel approach for components' vulnerability rating. The approach is inspired by recent work on embedding source code functions.  ...  We describe a workflow used to analyze the source code of the Android OS kernel and rate for a particular kind of bugginess that exposes a program to hacking.  ...  An embedding, or auto-encoding with LSTM; a vector in R128 for each function. 3. Heuristics-based feature a vector, one for each function. 4.  ... 
arXiv:2112.11214v1 fatcat:vwhn3xx6wzaoxnn6xi63mv3rju

A Lexico-Semantic Reading of Chimamanda Adichie'sPurple Hibiscus

Ebi Yeibo, Comfort Akerele
2015 International Journal of Language and Literature  
A key purpose for exploring the language of a text is to determine the extent to which a given author has organized and deployed its limitless potentials to encode or relate the intended message and social  ...  It is particularly used by British linguists for the vocabulary of language or sub-language especially of its stock of lexemes.  ...  messages, visions and themes embedded in the text.  ... 
doi:10.15640/ijll.v3n2a15 fatcat:2gr6l72vtrajdd3qhpjjrvdhge

Gamification as a Supportive Tool for School Children with Dyslexia

Dymora, Niemiec
2019 Informatics  
Its advantage is also that it does not have to be limited to one technology or method—it can be realized both through a simple scenario and a corkboard with results, it can also be embedded, e.g., in a  ...  The conducted study was based on the implementation of original algorithms and scenarios of gamification on mobile devices, especially smartphones.  ...  The first is that the control group, during both the first and second dictations, omitted a large part of the text.  ... 
doi:10.3390/informatics6040048 fatcat:grgzg6wrsbgqdppv7oewf7qmie

On Reliable Transmission of Data over Simple Wireless Channels

Pawel Gburzynski, Bozena Kaminska, Ashikur Rahman
2009 Journal of Computer Systems, Networks, and Communications  
Using a specific project as an example, we demonstrate how the constraints of a low-cost embedded wireless system get in the way of a workable solution precluding the use of popular schemes based on windows  ...  Standard protocols for reliable data transmission over unreliable channels are based on various Automatic Repeat reQuest (ARQ) schemes, whereby the sending node receives feedback from the receiver and  ...  Nothing stops B from decoding that request (the same way it would decode a similar request addressed to itself) and estimating for how long A will be transmitting the blocks.  ... 
doi:10.1155/2009/409853 fatcat:7nht3osezje4xlzkh3dptmrkwy

Extended low-rank plus diagonal adaptation for deep and recurrent neural networks

Yong Zhao, Jinyu Li, Kshitiz Kumar, Yifan Gong
2017 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Experimental results on the short message dictation (SMD) task show that the eLRPD adaptation can reduce the SD footprints by 82% for the SVD DNN and 96% for the LSTM-RNN over the linear adaptation, while  ...  We apply the extended LRPD (eLRPD) adaptation for the DNN and LSTM models with emphasis placed on the applicability of the adaptation to large-scale speech recognition systems.  ...  The proposed methods are evaluated on a short message dictation (SMD) task.  ... 
doi:10.1109/icassp.2017.7953116 dblp:conf/icassp/ZhaoLKG17 fatcat:vnltvdfpxzfl3noadl7ofx4nzu
« Previous Showing results 1 — 15 out of 2,269 results