DE eng

Search in the Catalogues and Directories

Hits 1 – 8 of 8

1
Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales ...
BASE
Show details
2
Interpreting intermediate convolutional layers of CNNs trained on raw speech ...
Beguš, Gašper; Zhou, Alan. - : arXiv, 2021
BASE
Show details
3
Interpreting intermediate convolutional layers in unsupervised acoustic word classification ...
Beguš, Gašper; Zhou, Alan. - : arXiv, 2021
BASE
Show details
4
Generative Adversarial Phonology: Modeling unsupervised phonetic and phonological learning with neural networks ...
Beguš, Gašper. - : arXiv, 2020
BASE
Show details
5
Local and non-local dependency learning and emergence of rule-like representations in speech data by Deep Convolutional Generative Adversarial Networks ...
Beguš, Gašper. - : arXiv, 2020
BASE
Show details
6
Identity-Based Patterns in Deep Convolutional Networks: Generative Adversarial Phonology and Reduplication ...
Beguš, Gašper. - : arXiv, 2020
BASE
Show details
7
Deep Sound Change: Deep and Iterative Learning, Convolutional Neural Networks, and Language Change ...
Beguš, Gašper. - : arXiv, 2020
BASE
Show details
8
CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks ...
Beguš, Gašper. - : arXiv, 2020
Abstract: How can deep neural networks encode information that corresponds to words in human speech into raw acoustic data? This paper proposes two neural network architectures for modeling unsupervised lexical learning from raw acoustic inputs, ciwGAN (Categorical InfoWaveGAN) and fiwGAN (Featural InfoWaveGAN), that combine a Deep Convolutional GAN architecture for audio data (WaveGAN; arXiv:1705.07904) with an information theoretic extension of GAN -- InfoGAN (arXiv:1606.03657), and propose a new latent space structure that can model featural learning simultaneously with a higher level classification and allows for a very low-dimension vector representation of lexical items. Lexical learning is modeled as emergent from an architecture that forces a deep neural network to output data such that unique information is retrievable from its acoustic outputs. The networks trained on lexical items from TIMIT learn to encode unique information corresponding to lexical items in the form of categorical variables in their ... : Published in Neural Networks ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
URL: https://arxiv.org/abs/2006.02951
https://dx.doi.org/10.48550/arxiv.2006.02951
BASE
Hide details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
8
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern