1 |
Modeling speech recognition and synthesis simultaneously: Encoding and decoding lexical and sublexical semantic information into speech with no access to speech data ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Identity-Based Patterns in Deep Convolutional Networks: Generative Adversarial Phonology and Reduplication ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Interpreting intermediate convolutional layers of CNNs trained on raw speech ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Identity-Based Patterns in Deep Convolutional Networks: Generative Adversarial Phonology and Reduplication ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Interpreting intermediate convolutional layers in unsupervised acoustic word classification ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Generative Adversarial Phonology: Modeling unsupervised phonetic and phonological learning with neural networks ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Local and non-local dependency learning and emergence of rule-like representations in speech data by Deep Convolutional Generative Adversarial Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Identity-Based Patterns in Deep Convolutional Networks: Generative Adversarial Phonology and Reduplication ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Deep Sound Change: Deep and Iterative Learning, Convolutional Neural Networks, and Language Change ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Modeling unsupervised phonetic and phonological learning in Generative Adversarial Phonology ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Generative Adversarial Phonology: Modeling Unsupervised Phonetic and Phonological Learning With Neural Networks
|
|
|
|
In: Front Artif Intell (2020)
|
|
Abstract:
Training deep neural networks on well-understood dependencies in speech data can provide new insights into how they learn internal representations. This paper argues that acquisition of speech can be modeled as a dependency between random space and generated speech data in the Generative Adversarial Network architecture and proposes a methodology to uncover the network's internal representations that correspond to phonetic and phonological properties. The Generative Adversarial architecture is uniquely appropriate for modeling phonetic and phonological learning because the network is trained on unannotated raw acoustic data and learning is unsupervised without any language-specific assumptions or pre-assumed levels of abstraction. A Generative Adversarial Network was trained on an allophonic distribution in English, in which voiceless stops surface as aspirated word-initially before stressed vowels, except if preceded by a sibilant [s]. The network successfully learns the allophonic alternation: the network's generated speech signal contains the conditional distribution of aspiration duration. The paper proposes a technique for establishing the network's internal representations that identifies latent variables that correspond to, for example, presence of [s] and its spectral properties. By manipulating these variables, we actively control the presence of [s] and its frication amplitude in the generated outputs. This suggests that the network learns to use latent variables as an approximation of phonetic and phonological representations. Crucially, we observe that the dependencies learned in training extend beyond the training interval, which allows for additional exploration of learning representations. The paper also discusses how the network's architecture and innovative outputs resemble and differ from linguistic behavior in language acquisition, speech disorders, and speech errors, and how well-understood dependencies in speech data can help us interpret how neural networks learn their representations.
|
|
Keyword:
Artificial Intelligence
|
|
URL: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7861218/ https://doi.org/10.3389/frai.2020.00044
|
|
BASE
|
|
Hide details
|
|
15 |
Modeling unsupervised phonetic and phonological learning in Generative Adversarial Phonology
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
16 |
Unnatural Phonology: A Synchrony-Diachrony Interface Approach
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Relativna kronologija naglasnih pojavov govora Žirovske kotline poljanskega narečja ; The Relative Chronology of Word-Prosodic Phenomena in the Local Dialect of the Žiri Basin (Poljana Dialect)
|
|
Beguš, Gašper. - : ZRC SAZU and Hall Center for the Humanities, 2011
|
|
BASE
|
|
Show details
|
|
|
|