Discovering discrete subword units with binarized autoencoders and hidden-Markov-model encoders

By Leonardo Badino, Alessio Mereta, Lorenzo Rosasco. 2015

46 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Computational Linguistics & Semantics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Representation & Self-Supervised Learning

In Computational Linguistics & Semantics

Citations in the corpus

Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks (2019, methodology): “In contrast to the feed-forward AEs of [14, 25, 26], we incorporate temporal context by using a convolutional encoder and deconvolutional decoder in our AE.”
A segmental framework for fully-unsupervised large-vocabulary speech recognition (2016, background): “The above approaches perform representation learning without regard to longer-spanning word-or phrase-like patterns in the data.”
The Zero Resource Speech Challenge 2015: Proposed Approaches and Results (2016, methodology): “The systems based around modeling the acoustic space in an unsupervised manner [3, 4, 6] provide insight into the effectiveness of these methods that could be transferred to supervised methods.”
Measuring the perceptual availability of phonological features during language acquisition using unsupervised binary stochastic autoencoders (2019, background): “Participating systems (Badino et al., 2015; Renshaw et al., 2015; Agenbag and Niesler, 2015; Chen et al., 2015; Baljekar et al., 2015; Räsänen et al., 2015; Lyzinski et al., 2015; Zeghidour et al., 2016; Heck et al., 2016; Srivastava and Shrivastava, 2016; Kamper et al., 2017b; Chen et al., 2017;…”
ABX-Discriminability Measures and Applications. (Mesures de discriminabilité ABX et applications) (2016, background): “They showed how the performance of such systems can be affected by the choice of acoustic features [35, 88, 96, 103], of an acoustic modeling method [87, 90, 97, 102, 105, 106] or the combination of both [107, 108].”
Self-Supervised Speech Representation Learning: A Review (2022, background): “In addition to the approaches discussed above, several other works on speech representation learning take inspiration from the AE framework [86], [87], [88], [89], [90], [91].”
Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning (2018, methodology): “Moreover our approach could be applicable to other neural network based approaches such as autoencoder [8] and Siamese network [7].”
A deep scattering spectrum — Deep Siamese network pipeline for unsupervised acoustic modeling (2016, background): “In previous work, several architectures have been explored to learn an acoustic model in an unsupervised or weakly-supervised way [2, 3, 4, 5].”
Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge (2020, background): “More recent studies have explored neural networks with intermediate discretization [20–23].”
Feature optimized DPGMM clustering for unsupervised subword modeling: A contribution to zerospeech 2017 (2017, unknown): “[4] make use of a deep auto-encoder that applies a threshold at the encoding layer to generate a binary representation of speech frames.”