cicyt UNIZAR

Sound

Authors and titles for recent submissions

[ total of 14 entries: 1-14 ]
[ showing up to 25 entries per page: fewer | more ]

Fri, 23 Feb 2018

[1]  arXiv:1802.08008 [pdf, other]
Title: Sounderfeit: Cloning a Physical Model with Conditional Adversarial Autoencoders
Authors: Stephen Sinclair
Comments: Published in the Brazilian Symposium on Computer Music (SBCM 2017)
Journal-ref: Proc. Brazilian Symp. on Comp. Music., 2017. p. 67--74
Subjects: Sound (cs.SD); Learning (cs.LG); Audio and Speech Processing (eess.AS)
[2]  arXiv:1802.07860 [pdf, other]
Title: Neural Predictive Coding using Convolutional Neural Networks towards Unsupervised Learning of Speaker Characteristics
Subjects: Sound (cs.SD); Computation and Language (cs.CL); Audio and Speech Processing (eess.AS)

Thu, 22 Feb 2018

[3]  arXiv:1802.07420 (cross-list from cs.CL) [pdf, other]
Title: Sequence-based Multi-lingual Low Resource Speech Recognition
Comments: 5 pages, 5 figures, to appear in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018)
Subjects: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)

Wed, 21 Feb 2018

[4]  arXiv:1802.06840 [pdf, other]
Title: Voice Impersonation using Generative Adversarial Networks
Comments: Accepted by 2018 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2018)
Subjects: Sound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
[5]  arXiv:1802.06984 (cross-list from cs.LG) [pdf, other]
Title: Fitting New Speakers Based on a Short Untranscribed Sample
Subjects: Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[6]  arXiv:1802.06941 (cross-list from cs.CL) [pdf]
Title: Distilling Knowledge Using Parallel Data for Far-field Speech Recognition
Subjects: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[7]  arXiv:1802.06861 (cross-list from cs.CL) [pdf]
Title: Interpreting DNN output layer activations: A strategy to cope with unseen data in speech recognition
Comments: 5 pages. arXiv admin note: substantial text overlap with arXiv:1708.09516
Subjects: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)

Tue, 20 Feb 2018

[8]  arXiv:1802.06412 (cross-list from cs.CL) [pdf, other]
Title: Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs
Comments: 5 pages, 3 figures, 2 tables, to appear in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018)
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Sound (cs.SD); Audio and Speech Processing (eess.AS); Machine Learning (stat.ML)
[9]  arXiv:1802.06209 (cross-list from cs.CL) [pdf]
Title: Sentiment Analysis on Speaker Specific Speech Data
Comments: Accepted and Published in 2017 IEEE International Conference on Intelligent Computing and Control (I2C2), 23 Jun - 24 Jun 2017, India
Subjects: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[10]  arXiv:1802.06182 (cross-list from eess.AS) [pdf, other]
Title: CREPE: A Convolutional Representation for Pitch Estimation
Comments: ICASSP 2018
Subjects: Audio and Speech Processing (eess.AS); Learning (cs.LG); Sound (cs.SD); Machine Learning (stat.ML)

Mon, 19 Feb 2018

[11]  arXiv:1802.06006 (cross-list from cs.CL) [pdf, other]
Title: Neural Voice Cloning with a Few Samples
Subjects: Computation and Language (cs.CL); Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[12]  arXiv:1802.06003 (cross-list from cs.CL) [pdf, ps, other]
Title: Structured-based Curriculum Learning for End-to-end English-Japanese Speech Translation
Subjects: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[13]  arXiv:1802.05853 (cross-list from cs.CL) [pdf]
Title: Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition
Comments: 5 pages
Subjects: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[14]  arXiv:1802.05792 (cross-list from cs.LG) [pdf]
Title: Masked Conditional Neural Networks for Automatic Sound Events Recognition
Comments: Restricted Boltzmann Machine, RBM, Conditional RBM, CRBM, Deep Belief Net, DBN, Conditional Neural Network, CLNN, Masked Conditional Neural Network, MCLNN, Environmental Sound Recognition, ESR
Journal-ref: IEEE International Conference on Data Science and Advanced Analytics (DSAA) Year: 2017, Pages: 389 - 394
Subjects: Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS); Machine Learning (stat.ML)
[ total of 14 entries: 1-14 ]
[ showing up to 25 entries per page: fewer | more ]

Disable MathJax (What is MathJax?)