Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Sri Rama Murty Kodukula"'
Publikováno v:
Circuits, Systems & Signal Processing; Jul2024, Vol. 43 Issue 7, p4487-4507, 21p
Publikováno v:
2022 National Conference on Communications (NCC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e72a1bf40a301c4593440d05ebb11b1d
https://doi.org/10.1109/ncc55593.2022.9806799
https://doi.org/10.1109/ncc55593.2022.9806799
Publikováno v:
Circuits, Systems, and Signal Processing. 39:5169-5197
This paper presents a new approach for unsupervised segmentation and labeling of acoustically homogeneous segments from the speech signals. The virtual labels, thus obtained, are used to build unsupervised acoustic models in the absence of manual tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::902bc9577b2533f1bb89c9b493a2456b
https://doi.org/10.1007/s00034-020-01408-8
https://doi.org/10.1007/s00034-020-01408-8
In this paper, we demonstrate the significance of restoring harmonics of the fundamental frequency (pitch) in deep neural network (DNN) based speech enhancement. We propose a sliding-window attention network to regress the spectral magnitude mask (SM
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::365c954468bc95925b3dc461e0d99417
https://doi.org/10.36227/techrxiv.15051972.v1
https://doi.org/10.36227/techrxiv.15051972.v1
Publikováno v:
IEEE Transactions on Multimedia. 21:1672-1680
A fixed dimensional representation for action clips of varying lengths has been proposed in the literature using aggregation models like bag-of-words and Fisher vector. These representations are high dimensional and require classification techniques
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e7c672690e7a6aebc2d2faad5d0b35e2
https://doi.org/10.1109/tmm.2018.2887021
https://doi.org/10.1109/tmm.2018.2887021
Publikováno v:
NCC
In the recent past, Deep neural networks became the most successful approach to extract the speaker embeddings. Among the existing methods, the x-vector system, that extracts a fixed dimensional representation from varying length speech signal, becam
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8af3bd277483dc4487baafd806280e81
https://doi.org/10.1109/ncc48643.2020.9056043
https://doi.org/10.1109/ncc48643.2020.9056043
Publikováno v:
NCC
Most of the speech enhancement algorithms rely on estimating the magnitude spectrum of the clean speech signal from that of the noisy speech signal using either spectral regression or spectral masking. Because of difficulty in processing the phase of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8419818145951fa2ef831c4b80de7ee0
https://doi.org/10.1109/ncc48643.2020.9056089
https://doi.org/10.1109/ncc48643.2020.9056089
Publikováno v:
ICIP
Actions can be recognized effectively when the various atomic attributes forming the action are identified and combined in the form of a representation. In this paper, a low-dimensional representation is extracted from a pool of attributes learned in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3cb546420bd53a77ec0cf36ab774c189
https://doi.org/10.1109/icip.2018.8451226
https://doi.org/10.1109/icip.2018.8451226
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 23:2371-2383
The phase spectrum of Fourier transform has received lesser prominence than its magnitude counterpart in speech processing. In this paper, we propose a method for parametric modeling of the phase spectrum, and discuss its applications in speech signa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db0c118fac49648753b1f31035f53381
https://doi.org/10.1109/taslp.2015.2479045
https://doi.org/10.1109/taslp.2015.2479045
Publikováno v:
Circuits, Systems, and Signal Processing. 35:2584-2609
Epochs are instants of significant excitation of vocal-tract system in speech production process. In this paper, we attempt to extract information about epochs from phase spectra of speech signals. The phase spectrum of speech is modelled as the resp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d5590974920f44306b82183ef83bf21c
https://doi.org/10.1007/s00034-015-0166-6
https://doi.org/10.1007/s00034-015-0166-6