Zobrazeno 1 - 10
of 933
pro vyhledávání: '"Oguz, H"'
Autor:
Cambier, Léopold, Bhiwandiwalla, Anahita, Gong, Ting, Nekuii, Mehran, Elibol, Oguz H, Tang, Hanlin
Training with larger number of parameters while keeping fast iterations is an increasingly adopted strategy and trend for developing better performing Deep Neural Network (DNN) models. This necessitates increased memory footprint and computational re
Externí odkaz:
http://arxiv.org/abs/2001.05674
Publikováno v:
Proc. Interspeech 2019 (2019): 729-733
In this work we introduce a semi-supervised approach to the voice conversion problem, in which speech from a source speaker is converted into speech of a target speaker. The proposed method makes use of both parallel and non-parallel utterances from
Externí odkaz:
http://arxiv.org/abs/1910.00067
This paper evaluates the effectiveness of a Cycle-GAN based voice converter (VC) on four speaker identification (SID) systems and an automated speech recognition (ASR) system for various purposes. Audio samples converted by the VC model are classifie
Externí odkaz:
http://arxiv.org/abs/1905.12531
Publikováno v:
ICASSP 2019
We present a rapid design methodology that combines automated hyper-parameter tuning with semi-supervised training to build highly accurate and robust models for voice commands classification. Proposed approach allows quick evaluation of network arch
Externí odkaz:
http://arxiv.org/abs/1905.04230
Autor:
Ocal, Orhan, Elibol, Oguz H., Keskin, Gokce, Stephenson, Cory, Thomas, Anil, Ramchandran, Kannan
We present a method for converting the voices between a set of speakers. Our method is based on training multiple autoencoder paths, where there is a single speaker-independent encoder and multiple speaker-dependent decoders. The autoencoders are tra
Externí odkaz:
http://arxiv.org/abs/1905.03864
We present a Cycle-GAN based many-to-many voice conversion method that can convert between speakers that are not in the training set. This property is enabled through speaker embeddings generated by a neural network that is jointly trained with the C
Externí odkaz:
http://arxiv.org/abs/1905.02525
Publikováno v:
Communications Earth & Environment, Vol 3, Iss 1, Pp 1-12 (2022)
Several central Andean basins may have formed from the coupling of crustal deformation to dripping of the upper mantle lithosphere, according to three- dimensional scaled analogue experiments
Externí odkaz:
https://doaj.org/article/fc5c9a1c875d4730bbbe06cae87e3ca4
Publikováno v:
In Gondwana Research May 2022 105:399-415
Autor:
Köster, Urs, Webb, Tristan J., Wang, Xin, Nassar, Marcel, Bansal, Arjun K., Constable, William H., Elibol, Oğuz H., Gray, Scott, Hall, Stewart, Hornof, Luke, Khosrowshahi, Amir, Kloss, Carey, Pai, Ruby J., Rao, Naveen
Deep neural networks are commonly developed and trained in 32-bit floating point format. Significant gains in performance and energy efficiency could be realized by training and inference in numerical formats optimized for deep learning. Despite adva
Externí odkaz:
http://arxiv.org/abs/1711.02213
Autor:
Kollia, Varvara, Elibol, Oguz H.
This paper investigates the use of distributed processing on the problem of emotion recognition from physiological sensors using a popular machine learning library on distributed mode. Specifically, we run a random forests classifier on the biosignal
Externí odkaz:
http://arxiv.org/abs/1609.02631