A Deep Generative Model of Vowel Formant Typology

Cotterell, Ryan; Eisner, Jason

doi:10.18653/v1/n18-1004

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generative models have been in the vanguard of unsupervised learning. Techniques such as GMMs [62], Boltzmann machines [63], variational autoencoders [64], and generative adversarial networks (GANs) [65] have been successfully applied in numerous computer vision [66], speech recognition and generation [67], and natural language [68, 69] tasks. Those algorithms try to capture inner data probabilistic distribution to generate new similar data [70].…”

Section: Related Workmentioning

confidence: 99%

On the generalisation capabilities of Fisher vector‐based face presentation attack detection

2021

View full text Add to dashboard Cite

In past decades, the broad development experienced by biometric systems has unveiled several threats that may decrease their trustworthiness. These are attack presentations that can be easily carried out by a non‐authorised subject to gain access to the biometric system. To mitigate those security concerns, most face presentation attack detection techniques have reported good detection performance when they are evaluated on known presentation attack instruments (PAIs) and under acquisition conditions. In contrast, for more realistic scenarios, existing algorithms face difficulties in detecting unknown PAI species which are only included in the test set. A feature space based on Fisher Vectors computed from compact binarised statistical image features histograms, which allows discovering semantic feature subsets from known samples to enhance the detection of unknown attacks is presented. This representation, which is evaluated for challenging unknown attacks taken from freely available facial databases, reports promising results. A Bona Fide Presentation Classification Error Rate 100 under 17% together with an area under the receiving operating characteristic curve of over 98% can be achieved in the presence of unknown attacks. In addition, by training a limited number of parameters, the method is able to achieve state‐of‐the‐art deep learning‐based approaches for cross‐dataset scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

On the generalisation capabilities of Fisher vector‐based face presentation attack detection

2021

View full text Add to dashboard Cite

show abstract

“…Feature prediction is a commonly used task in evaluating how well a given model is able to explain the typological features of languages (Daumé III and Campbell, 2007;Malaviya et al, 2017;Cotterell and Eisner, 2018;Ponti et al, 2018;Bjerva et al, 2019a). This is an important task which can highlight the extent to which a model has learned interdependencies between languages and features.…”

Section: Predicting Typological Featuresmentioning

confidence: 99%

Uncovering Probabilistic Implications in Typological Knowledge Bases

Bjerva

Kementchedjhieva

Cotterell

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

The study of linguistic typology is rooted in the implications we find between linguistic features, such as the fact that languages with object-verb word ordering tend to have postpositions. Uncovering such implications typically amounts to time-consuming manual processing by trained and experienced linguists, which potentially leaves key linguistic universals unexplored. In this paper, we present a computational model which successfully identifies known universals, including Greenberg universals, but also uncovers new ones, worthy of further linguistic investigation. Our approach outperforms baselines previously used for this problem, as well as a strong baseline from knowledge base population.

show abstract