Zobrazeno 1 - 10
of 213
pro vyhledávání: '"Finkelstein, Adam"'
Perceptual evaluation constitutes a crucial aspect of various audio-processing tasks. Full reference (FR) or similarity-based metrics rely on high-quality reference recordings, to which lower-quality or corrupted versions of the recording may be comp
Externí odkaz:
http://arxiv.org/abs/2310.09388
Many audio processing tasks require perceptual assessment. However, the time and expense of obtaining ``gold standard'' human judgments limit the availability of such data. Most applications incorporate full reference or other similarity-based metric
Externí odkaz:
http://arxiv.org/abs/2206.13411
Autor:
Hoskins, Meloria A.1 (AUTHOR) mhoskins@pennstatehealth.psu.edu, Finkelstein, Adam1 (AUTHOR) afinkelstein@pennstatehealth.psu.edu, Rashid, Aisha1 (AUTHOR) arashid@pennstatehealth.psu.edu, Ziegler, Olivia2 (AUTHOR) oziegler@pennstatehealth.psu.edu, Mankarious, Marc M.2 (AUTHOR) mmankarious@pennstatehealth.psu.edu, Benavides, Jorge V.3 (AUTHOR), Pameijer, Colette R.3 (AUTHOR) cpameijer@pennstatehealth.psu.edu
Publikováno v:
Journal of Clinical Medicine. Apr2024, Vol. 13 Issue 8, p2358. 8p.
Autor:
Greene, Alicia C., Mankarious, Marc M., Finkelstein, Adam, El-Mallah, Jessica C., Kulaylat, Audrey S., Kulaylat, Afif N.
Publikováno v:
In Journal of Surgical Research March 2024 295:399-406
Many speech processing methods based on deep learning require an automatic and differentiable audio metric for the loss function. The DPAM approach of Manocha et al. learns a full-reference metric trained directly on human judgments, and thus correla
Externí odkaz:
http://arxiv.org/abs/2102.05109
Deep learning for image processing typically treats input imagery as pixels in some color space. This paper proposes instead to learn from program traces of procedural fragment shaders -- programs that generate images. At each pixel, we collect the i
Externí odkaz:
http://arxiv.org/abs/2102.04533
Real-world audio recordings are often degraded by factors such as noise, reverberation, and equalization distortion. This paper introduces HiFi-GAN, a deep learning method to transform recorded speech to sound as though it had been recorded in a stud
Externí odkaz:
http://arxiv.org/abs/2006.05694
Autor:
Manocha, Pranay, Finkelstein, Adam, Zhang, Richard, Bryan, Nicholas J., Mysore, Gautham J., Jin, Zeyu
Many audio processing tasks require perceptual assessment. The ``gold standard`` of obtaining human judgments is time-consuming, expensive, and cannot be used as an optimization criterion. On the other hand, automated metrics are efficient to compute
Externí odkaz:
http://arxiv.org/abs/2001.04460
Autor:
Fried, Ohad, Tewari, Ayush, Zollhöfer, Michael, Finkelstein, Adam, Shechtman, Eli, Goldman, Dan B, Genova, Kyle, Jin, Zeyu, Theobalt, Christian, Agrawala, Maneesh
Editing talking-head video to change the speech content or to remove filler words is challenging. We propose a novel method to edit talking-head video based on its transcript to produce a realistic output video in which the dialogue of the speaker ha
Externí odkaz:
http://arxiv.org/abs/1906.01524
Location-aware applications play an increasingly critical role in everyday life. However, satellite-based localization (e.g., GPS) has limited accuracy and can be unusable in dense urban areas and indoors. We introduce an image-based global localizat
Externí odkaz:
http://arxiv.org/abs/1710.10687