1 |
MAGIC DUST FOR CROSS-LINGUAL ADAPTATION OF MONOLINGUAL WAV2VEC-2.0
|
|
|
|
In: ICASSP 2022 ; https://hal.archives-ouvertes.fr/hal-03544515 ; ICASSP 2022, May 2022, Singapour, Singapore (2022)
|
|
BASE
|
|
Show details
|
|
5 |
Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0 ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Text-Free Image-to-Speech Synthesis Using Learned Segmental Units ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation? ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Mitigating Biases in Toxic Language Detection through Invariant Rationalization ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Mitigating Biases in Toxic Language Detection through Invariant Rationalization ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning
|
|
|
|
In: Interspeech 2020 ; https://hal.archives-ouvertes.fr/hal-02912029 ; Interspeech 2020, Oct 2020, Shanghai, China (2020)
|
|
Abstract:
International audience ; Probabilistic Latent Variable Models (LVMs) provide an alternative to self-supervised learning approaches for linguistic representation learning from speech. LVMs admit an intuitive probabilistic interpretation where the latent structure shapes the information extracted from the signal. Even though LVMs have recently seen a renewed interest due to the introduction of Vari-ational Autoencoders (VAEs), their use for speech representation learning remains largely unexplored. In this work, we propose Convolutional Deep Markov Model (ConvDMM), a Gaus-sian state-space model with non-linear emission and transition functions modelled by deep neural networks. This unsupervised model is trained using black box variational inference. A deep convolutional neural network is used as an inference network for structured variational approximation. When trained on a large scale speech dataset (LibriSpeech), ConvDMM produces features that significantly outperform multiple self-supervised feature extracting methods on linear phone classification and recognition on the Wall Street Journal dataset. Furthermore, we found that ConvDMM complements self-supervised methods like Wav2Vec and PASE, improving on the results achieved with any of the methods alone. Lastly, we find that ConvDMM features enable learning better phone recognizers than any other features in an extreme low-resource regime with few labelled training examples.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]; Neural Variational Latent Variable Model; Structured Variational Inference; Unsupervised Speech Representation Learning
|
|
URL: https://hal.archives-ouvertes.fr/hal-02912029/file/convDMM_arxiv.pdf https://hal.archives-ouvertes.fr/hal-02912029/document https://hal.archives-ouvertes.fr/hal-02912029
|
|
BASE
|
|
Hide details
|
|
11 |
Similarity Analysis of Contextual Word Representation Models ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
What Was Written vs. Who Read It: News Media Profiling Using Text Analysis and Social Media Context ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Improved Speech Representations with Multi-Target Autoregressive Predictive Coding ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Classifying Alzheimer's Disease Using Audio and Text-Based Representations of Speech
|
|
|
|
In: Frontiers (2020)
|
|
BASE
|
|
Show details
|
|
19 |
Identification of digital voice biomarkers for cognitive health
|
|
|
|
In: Explor Med (2020)
|
|
BASE
|
|
Show details
|
|
20 |
On the Linguistic Representational Power of Neural Machine Translation Models
|
|
|
|
In: Computational Linguistics, Vol 46, Iss 1, Pp 1-52 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
|
|