Co-occurring keywords · papers mentioning both
multi-level acoustic feature
(1)
frame-level speech representation
(1)
zero-resource language
(1)
transformer encoder-decoder
(1)
factorized hierarchical variational autoencoder
(1)
subword modeling
(1)
dirichlet process gaussian mixture model
(1)
acoustic unit discovery
(1)
feature fusion
(1)
variational autoencoder
(1)
Papers
A Multi-level Acoustic Feature Extraction Framework for Transformer Based End-to-End Speech Recognition
Interspeech 2022
Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery
Interspeech 2019
Improving Unsupervised Subword Modeling via Disentangled Speech Representation Learning and Transformation
Interspeech 2019
Speaker Adversarial Training of DPGMM-Based Feature Extractor for Zero-Resource Languages
Interspeech 2019