Zobrazeno 1 - 10
of 66
pro vyhledávání: '"John N. Gowdy"'
Publikováno v:
IEEE Journal of Biomedical and Health Informatics. 19:825-831
This paper considers the problem of recognizing eating gestures by tracking wrist motion. Eating gestures are activities commonly undertaken during the consumption of a meal, such as sipping a drink of liquid or using utensils to cut food. Each of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79ca0043152a1fc02cb6f58ef510fa98
https://doi.org/10.1109/jbhi.2014.2329137
https://doi.org/10.1109/jbhi.2014.2329137
Autor:
Sanjay P. Patil, John N. Gowdy
Publikováno v:
Speech Communication. 67:78-91
In this study we propose a noise estimation technique based on spectral sparsity, detected by using the harmonic property of voiced segments of the speech. We estimate the frame to frame phase difference for clean speech, in the baseband Short Time F
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bbc1a218ff31c8240267d9740e0beb10
https://doi.org/10.1016/j.specom.2014.11.003
https://doi.org/10.1016/j.specom.2014.11.003
Autor:
Sanjay P. Patil, John N. Gowdy
Publikováno v:
ICASSP
Performance of traditional speech enhancement techniques like spectral subtraction and log-Minimum Mean Squared Error Short Time Spectral Amplitude (log-MMSE STSA) estimation degrades in presence of highly non-stationary noises like babble noise. Thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::acf06492db36e06aaa5720538107bcc9
https://doi.org/10.1109/icassp.2014.6854774
https://doi.org/10.1109/icassp.2014.6854774
Autor:
Yiqiao Chen, John N. Gowdy
Publikováno v:
2013 IEEE International Conference on Signal Processing, Communication and Computing (ICSPCC 2013).
Linear prediction (LP) and complex cepstrum (CC) approaches have been shown to be effective for extracting glottal flow pulses (GFPs). This paper proposes a new approach, which first employs an odd-order LP analysis to find parameters of an all-pole
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e9008e583c43dd1cfc0249ffd63f5be
https://doi.org/10.1109/icspcc.2013.6664146
https://doi.org/10.1109/icspcc.2013.6664146
Publikováno v:
ICASSP (1)
In this paper, we propose a model based on dynamic Bayesian networks (DBN) to integrate information from multiple audio and visual streams. We also compare the DBN based system (implemented using the Graphical Model Toolkit (GMTK)) with a classical H
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4cdb6a4e442f0199322d093de5f6a8e2
https://doi.org/10.1109/icassp.2004.1326155
https://doi.org/10.1109/icassp.2004.1326155
Autor:
Eric Patterson, John N. Gowdy
Publikováno v:
ICASSP (5)
Audio-visual speech recognition is an area with great potential to help solve challenging problems in speech processing. Difficulties due to background noise are significantly reduced by the additional information provided by extra visual features. T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b6e5930d57b6464c2e865094cb38e61
https://doi.org/10.1109/icassp.2003.1200087
https://doi.org/10.1109/icassp.2003.1200087
Autor:
John N. Gowdy, M.S. Scordilis
Publikováno v:
Proceedings. IEEE Energy and Information Technologies in the Southeast'.
A parallel distributed model is developed for the text-to-speech synthesis problem. This model includes a procedure which marks those incoming letters which are soundless, but which modify the pronunciation of their neighbors. Neural-network simulati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::31a2b977c302ec4c14cd7ae75afa9f8c
https://doi.org/10.1109/secon.1989.132503
https://doi.org/10.1109/secon.1989.132503
Autor:
M.S. Scordilis, John N. Gowdy
Publikováno v:
ICASSP
Although a number of algorithms exist for the generation of the fundamental frequency contour in automatic text-to-speech conversion systems, the absence of a general theory of intonation still prevents the correct derivation of this important featur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a88cac0d6284e3b00bcd36a9a2e7b691
https://doi.org/10.1109/icassp.1989.266404
https://doi.org/10.1109/icassp.1989.266404
Autor:
John N. Gowdy, V.Z. Kepuska
Publikováno v:
Proceedings. IEEE Energy and Information Technologies in the Southeast'.
A neural-network-based system for phonemic speech recognition is described. The self-organized feature map algorithm developed by T. Kohonen (1988) is used for the network model. The solution to the problem of overlap of feature vectors that correspo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e9f9693b9a12ce3933edede8de9b1cc7
https://doi.org/10.1109/secon.1989.132504
https://doi.org/10.1109/secon.1989.132504
Autor:
John N. Gowdy, S. Easwaran
Publikováno v:
Proceedings IEEE Southeastcon '92.
A novel algorithm for codebook initialization for use with the K-means algorithm for codebook generation is presented. This algorithm was shown to result in better codebooks at considerably reduced generation time compared to Lloyd's algorithm and to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d8503bf341d6f24fab8ae734f35cb49
https://doi.org/10.1109/secon.1992.202395
https://doi.org/10.1109/secon.1992.202395