28,344 Hits in 7.3 sec

Speech Technology Progress Based on New Machine Learning Paradigm

Vlado Delić, Zoran Perić, Milan Sečujski, Nikša Jakovljević, Jelena Nikolić, Dragiša Mišković, Nikola Simić, Siniša Suzić, Tijana Delić
2019 Computational Intelligence and Neuroscience  
Speech technologies have been developed for decades as a typical signal processing area, while the last decade has brought a huge progress based on new machine learning paradigms.  ...  To conclude, the main intention of this article is to highlight recent achievements and challenges based on new machine learning paradigms that, over the last decade, had an immense impact in the field  ...  Acknowledgments e work described in this paper was supported in part by the Ministry of Education, Science and Technological Development of the Republic of Serbia, through the project "Development of Dialogue  ... 
doi:10.1155/2019/4368036 pmid:31341467 pmcid:PMC6614991 fatcat:yfwrwisz7jgrtlijfpj7rkuuoi

Challenges in adopting speech recognition

Li Deng, Xuedong Huang
2004 Communications of the ACM  
69 I n recent years, significant progress has been made in advancing speech recognition technology, making speech an effective modality in both telephony and multimodal human-machine interaction.  ...  However, speech recognition technology has not been widely accepted in our society.  ...  Historical progress on machine speech recognition performance.  ... 
doi:10.1145/962081.962108 fatcat:et53nmqjrfgllgv3cvapjdsuay

Cognitive computing journey

David Nahamoo
2014 Proceedings of the first workshop on Parallel programming for analytics applications - PPAA '14  
While the journey has been difficult and slow, the progress in Machine Learning, Optimization Techniques and advancement in Deep Belief Networks offers promising ways to engineer cognitive systems.  ...  Building intelligent machines has been a long dream of humanity.  ...  Cognitive computing is a fundamentally new computing paradigm for tackling real world problems, exploiting enormous amounts of information using massively parallel machines that interact with humans and  ... 
doi:10.1145/2567634.2567646 dblp:conf/ppopp/Nahamoo14 fatcat:qu5luucx6ffk5hp2wuqwrkkh34

The speech synthesis phoneticians need is both realistic and controllable

Zofia Malisz, Gustav Eje Henter, Cassia Valentini-Botinhao, Oliver Watts, Jonas Beskow, Joakim Gustafson
2019 Zenodo  
This latest leap was ushered by powerful methods in machine learning, particularly deep learning, on large amounts of data (Watts et al., 2016) .  ...  Xu, Y., & Prom-On, S. (2014) Figure 1 . 1 Schematic history of speech synthesis: black dots are TTS systems, dashed arrows show technological paradigm shifts.  ... 
doi:10.5281/zenodo.3246014 fatcat:bwhq6h4hr5ftjm7pnnewzvtcdy

Significant Enhancements in Machine Translation by Various Deep Learning Approaches

Alpana Upadhyay
2017 American Journal of Computer Science and Information Technology  
A new and transforming technology for natural language processing and speech processing is deep learning.  ...  This technique of machine learning changes the perspective of addressing natural language and speech technologies considerably.  ...  This new paradigm employs attention based model with encoder decoder style to figure out with an end to end neural machine translation system [6] .  ... 
doi:10.21767/2349-3917.100008 fatcat:sc4mccb7ofdhjkhcka5c4jraza

Advanced Signal Processing and Adaptive Learning Methods

Zoran Perić, Vlado Delić, Zoran Stamenković, David Pokrajac
2019 Computational Intelligence and Neuroscience  
Gan et al. e paper entitled "Speech Technology Progress Based on New Machine Learning Paradigm" by V.  ...  Delić et al. provides an overview of speech technologies development as a typical signal processing area. e authors provide an analysis of the nature of speech signal and processing, corresponding machine  ...  Computer Games Technology Scienti c Programming Submit your manuscripts at  ... 
doi:10.1155/2019/5428615 pmid:31781180 pmcid:PMC6875201 fatcat:v6yhe2452nanfmgf5zx2ees76m

Developments and directions in speech recognition and understanding, Part 1 [DSP Education]

J. Baker, Li Deng, J. Glass, S. Khudanpur, Chin-hui Lee, N. Morgan, D. O'Shaughnessy
2009 IEEE Signal Processing Magazine  
He works on the application of information theoretic and statistical methods to human language technologies, including automatic speech recognition, machine translation, and information retrieval.  ...  The goal of this research program is to create self-adaptive (or self-learning) speech technology.  ... 
doi:10.1109/msp.2009.932166 fatcat:agpgfpsgmrcljl7izgbdk44gxu

Review of Design of Speech Recognition and Text Analytics based Digital Banking Customer Interface and Future Directions of Technology Adoption [article]

Amal K Saha
2017 arXiv   pre-print
The latest twist in this evolution is adoption of natural language processing and speech recognition in the user interface between the human and the system and use of machine learning and advanced analytics  ...  Banking is one of the most significant adopters of cutting-edge information technologies.  ...  ecosystem using a prototype built by us, and share analysis of user interface based on machine learning, and also speculate on future directions.  ... 
arXiv:1712.04640v1 fatcat:v3tqeuzubragtl2zdpftyhawx4

KEYNOTE SPEECH I AI and Machine Learning for Disease Incidence Modeling

Nitin Kumar Tripathi
2020 2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)  
WEKA machine learning tool with two classifier techniques, Multi-Layer Perceptron (MLP) and J48 were used with three test options, 10-fold cross-validation, percentile split, and supplied test.  ...  This study investigated the influence of climate factors on the incidence of malaria in the in India.  ...  The next stage involves training a machine learning classifier to identify messages with emoticons and images for a moderator to appropriately classify and tag them as offering specific support.  ... 
doi:10.1109/ic2ie50715.2020.9274624 fatcat:adkafxw7hze3zcuuqimbno2ita

Towards a unified theory of spoken language processing

R.K. Moore
2005 Fourth IEEE Conference on Cognitive Informatics, 2005. (ICCI 2005).  
Spoken Language Processing is arguably the most sophisticated behaviour of the most complex organism in the known universe and, unsurprisingly, scientists still have much to learn about how it works.  ...  This paper discusses these issues, and presents an argument in favour of the derivation of a 'unifying theory' that would be capable of explaining and predicting both human and machine spoken language  ...  Minor adaptation takes place (e.g. to accommodate a change in noise level) but such systems do not 'learn' to handle new concepts or tasks that arise in the course of an ongoing interaction.  ... 
doi:10.1109/coginf.2005.1532629 dblp:conf/IEEEicci/Moore05 fatcat:vdaajyvu4jc4poublmqwmo5nnq

Summary of the 2015 NIST Language Recognition i-Vector Machine Learning Challenge

Audrey Tong, Craig Greenberg, Alvin Martin, Desire Banse, John Howard, Hui Zhao, George Doddington, Daniel Garcia-Romero, Alan McCree, Douglas Reynolds, Elliot Singer, Jaime Hernandez-Cordero (+1 others)
2016 Odyssey 2016  
language recognition problem, exploring new ideas in machine learning for use in language recognition, and improving recognition accuracy.  ...  The Language Recognition i-Vector Machine Learning Challenge, taking place over a period of four months, was well-received with 56 participants from 44 unique sites and over 3700 submissions, surpassing  ...  of the speech processing community to tackle the language recognition problem, exploring new ideas in machine learning for use in language recognition, and improving the performance of the technology,  ... 
doi:10.21437/odyssey.2016-43 dblp:conf/odyssey/TongGMBHZDGMRSH15 fatcat:b7f2qlkr3nbubbnw5iffccdvmu

Are We There Yet? Research in Commercial Spoken Dialog Systems [chapter]

Roberto Pieraccini, David Suendermann, Krishna Dayanidhi, Jackson Liscombe
2009 Lecture Notes in Computer Science  
Yet based on a simple finite state machine design paradigm, dialog systems reached today a higher level of complexity.  ...  At the same time new methods for evaluating the subjective caller experience are available.  ...  The main point of the review was that research and commercial endeavors within the SDS technology have different goals and therefore aim at different paradigms for building interactive systems based on  ... 
doi:10.1007/978-3-642-04208-9_3 fatcat:3xr2cp2tangldjrng4qgwxqxf4

Towards human-like and transhuman perception in AI 2.0: a review

Yong-hong Tian, Xi-lin Chen, Hong-kai Xiong, Hong-liang Li, Li-rong Dai, Jing Chen, Jun-liang Xing, Jing Chen, Xi-hong Wu, Wei-min Hu, Yu Hu, Tie-jun Huang (+1 others)
2017 Frontiers of Information Technology & Electronic Engineering  
and learning engines.  ...  in an actual auditory setting; (3) speech perception and computation in a natural interaction setting; (4) autonomous learning of perceptual information; (5) large-scale perceptual information processing  ...  Speech perception and computing Speech perception and computing are together one of the core technologies to achieve man-machine interaction in the AI 2.0 era.  ... 
doi:10.1631/fitee.1601804 fatcat:rvcb4nvcr5borbhissvbevyce4

Natural Human-Human-System Interaction [chapter]

Niels Ole Bernsen
2001 Frontiers of Human-Centered Computing, Online Communities and Virtual Environments  
Recent progress in speech technologies has managed to establish a powerful application paradigm, i.e. that of natural task-oriented spoken language dialogue systems.  ...  On the backdrop of the natural HHSI model and the rapidly changing environment of advanced systems research, the types of research that are likely to be needed in the future are discussed.  ...  In those four decades, the environment in which research progress was made has changed dramatically, leading to entirely new perspectives for speech technology research.  ... 
doi:10.1007/978-1-4471-0259-5_25 fatcat:qnn5u7smijazlelezimslntzfi

How Mature Is the Field of Machine Learning? [chapter]

Marcello Pelillo, Teresa Scantamburlo
2013 Lecture Notes in Computer Science  
of much of contemporary machine learning research.  ...  Our motivating question can in fact be seen simply as an excuse to analyze the current status of the machine learning field using Kuhn's image of scientific progress, and to discuss the philosophical underpinnings  ...  The revolution results in a paradigm shift, after which a discipline returns to a normal phase,based this time on a new accepted framework.  ... 
doi:10.1007/978-3-319-03524-6_11 fatcat:br23du4brvcbdmfj6w64rym2wm
« Previous Showing results 1 — 15 out of 28,344 results