Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Sunil Bharitkar"'
Autor:
Sunil Bharitkar
Publikováno v:
2022 IEEE Workshop on Signal Processing Systems (SiPS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::94d4de8f501c711264f58541ad4d6148
https://doi.org/10.1109/sips55645.2022.9919258
https://doi.org/10.1109/sips55645.2022.9919258
Autor:
Sunil Bharitkar
Publikováno v:
ICASSP
The automatic classification of content is an essential requirement for multimedia applications. Present research for audio-based classifiers uses short- and long-term analysis of signals, with temporal and spectral features. In our prior study, we p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4beb31747e4c9073a92df718673d52f0
https://doi.org/10.1109/icassp40776.2020.9053187
https://doi.org/10.1109/icassp40776.2020.9053187
Autor:
Sunil Bharitkar
Publikováno v:
ICMLA
Automatic content classification is an essential problem for multimedia applications. In this paper, we present a metadata synthesis approach, using real-world distributions, and a machine learning (ML) model for classifying content for local and str
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::66b970802cdc5fc1fe746b84bd593112
https://doi.org/10.1109/icmla.2019.00025
https://doi.org/10.1109/icmla.2019.00025
Autor:
Sunil Bharitkar
Publikováno v:
ICMLA
Data transforms, parameter re-normalization, and activation functions have gained significant attention in the neural network community over the past several years for improving convergence speed. The results in the literature are for computer vision
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f67e45f29eb0f3e632ab4a7af682090
https://doi.org/10.1109/icmla.2019.00065
https://doi.org/10.1109/icmla.2019.00065
Publikováno v:
ICCE-Berlin
An automatic content classification technique is an essential tool in multimedia applications. Present research for audio-based classifiers look at short- and long-term analysis of signals, using both temporal and spectral features as well as using a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e78db07890581205889149f80d94c31
https://doi.org/10.1109/icce-berlin47944.2019.8966204
https://doi.org/10.1109/icce-berlin47944.2019.8966204
Autor:
Sunil Bharitkar
Publikováno v:
ICCE-Berlin
This paper presents a deep-learning technique for modeling Head-related Transfer Function (HRTF) using a large data-set from IRCAM [7] of 49 subjects with 115 directions/subject. We use a log-spectral distortion metric that we have used to optimize t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8bcb87d898502c8db866061cde84263c
https://doi.org/10.1109/icce-berlin47944.2019.8966196
https://doi.org/10.1109/icce-berlin47944.2019.8966196
Publikováno v:
APSIPA
Ipsilateral and contralateral head-related transfer functions (HRTF), $H_{\mathbf{ipsi}}(\omega, r,\phi,\theta)$ and $H_{\mathbf{contra}}(\omega, r,\phi,\theta)$ , are used for creating the perception of a virtual sound source at an arbitrary distanc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f53fabeab40df5f974cbfc91711353a
https://doi.org/10.23919/apsipa.2018.8659495
https://doi.org/10.23919/apsipa.2018.8659495
Publikováno v:
SMPTE Motion Imaging Journal. 121:30-45
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d4955f668f861b09e907f4fd5c335eab
https://doi.org/10.5594/j18246xy
https://doi.org/10.5594/j18246xy
Autor:
Sunil Bharitkar, Chris Kyriakakis
Publikováno v:
IEEE Transactions on Audio, Speech and Language Processing. 15:542-551
In this paper, a new method, using the Sammon map, is proposed for visualizing room responses and room response equalization. Specifically, the map provides an important perspective on the formation of clusters of acoustic room responses when cluster
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::79cc415abdb38ae1c6ea340e75de6447
https://doi.org/10.1109/tasl.2006.881683
https://doi.org/10.1109/tasl.2006.881683
Autor:
Jerry M. Mendel, Sunil Bharitkar
Publikováno v:
IEEE Transactions on Neural Networks. 11:879-888
A new neuron activation function based on a property found in physical systems--hysteresis--is proposed. We incorporate this neuron activation in a fully connected dynamical system to form the hysteretic Hopfield neural network (HHNN). We then presen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f3c40c021ec3edc412da1dcd8e68f2d
https://doi.org/10.1109/72.857769
https://doi.org/10.1109/72.857769