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
|
|
2 |
End-to-end speaker segmentation for overlap-aware resegmentation
|
|
|
|
In: Interspeech 2021 ; https://hal-univ-lemans.archives-ouvertes.fr/hal-03257524 ; Interspeech 2021, Aug 2021, Brno, Czech Republic ; https://www.interspeech2021.org/ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Transdisciplinary Analysis of a Corpus of French Newsreels: The ANTRACT Project
|
|
|
|
In: ISSN: 1938-4122 ; Digital Humanities Quarterly ; https://hal.archives-ouvertes.fr/hal-03166755 ; Digital Humanities Quarterly, Alliance of Digital Humanities, 2021, Special Issue on AudioVisual Data in DH, 15 (1) ; http://digitalhumanities.org/dhq/ (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0 ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Where are we in Named Entity Recognition from Speech?
|
|
|
|
In: 12th International Conference on Language Resources and Evaluation (LREC) ; https://hal.archives-ouvertes.fr/hal-02475026 ; 12th International Conference on Language Resources and Evaluation (LREC), May 2020, Marseille, France ; https://aclanthology.org/2020.lrec-1.556/ (2020)
|
|
BASE
|
|
Show details
|
|
6 |
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
|
|
7 |
CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Collective memory shapes the organization of individual memories in the medial prefrontal cortex
|
|
|
|
In: EISSN: 2397-3374 ; Nature Human Behaviour ; https://halshs.archives-ouvertes.fr/halshs-02416130 ; Nature Human Behaviour, Nature Research 2019, ⟨10.1038/s41562-019-0779-z⟩ (2019)
|
|
BASE
|
|
Show details
|
|
10 |
Effective keyword search for low-resourced conversational speech
|
|
|
|
In: icassp 2017 ; https://hal.archives-ouvertes.fr/hal-01744176 ; icassp 2017, IEEE, Mar 2017, La Nouvelle Orléans, United States (2017)
|
|
BASE
|
|
Show details
|
|
11 |
An investigation into language model data augmentation for low-resourced STT and KWS
|
|
|
|
In: IEEE International Conference on Acoustics, Speech, and Signal Processing ; https://hal.archives-ouvertes.fr/hal-01837171 ; IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, Mar 2017, New Orleans, United States (2017)
|
|
BASE
|
|
Show details
|
|
12 |
Language Recognition for Dialects and Closely Related Languages
|
|
|
|
In: Odyssey 2016 ; https://hal.archives-ouvertes.fr/hal-01744188 ; Odyssey 2016, Jun 2016, Bilbao, Spain (2016)
|
|
BASE
|
|
Show details
|
|
13 |
Language Model Data Augmentation for Keyword Spotting
|
|
|
|
In: Annual Conference of the International Speech Communication Association ; https://hal.archives-ouvertes.fr/hal-01837186 ; Annual Conference of the International Speech Communication Association , Jan 2016, San Francisco, United States (2016)
|
|
BASE
|
|
Show details
|
|
14 |
Investigating techniques for low resource conversational speech recognition
|
|
|
|
In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ; 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016) ; https://hal-univ-lemans.archives-ouvertes.fr/hal-01515254 ; 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), Mar 2016, Shangai, China. pp.5975-5979, ⟨10.1109/ICASSP.2016.7472824⟩ ; www.icassp2016.org (2016)
|
|
BASE
|
|
Show details
|
|
16 |
Investigating Techniques for Low Resource Conversational Speech Recognition
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Traduction de la parole dans le projet RAPMAT
|
|
|
|
In: Journées d'Études sur la Parole ; https://hal.archives-ouvertes.fr/hal-01843418 ; Journées d'Études sur la Parole, Jan 2014, Le Mans, France (2014)
|
|
BASE
|
|
Show details
|
|
19 |
Boosting bonsai trees for efficient features combination : application to speaker role identification
|
|
|
|
In: Interspeech ; https://hal.inria.fr/hal-01025171 ; Interspeech, Sep 2014, Singapour, Singapore (2014)
|
|
BASE
|
|
Show details
|
|
20 |
Development of a Korean speech recognition system with little annontated data
|
|
|
|
In: International Workshop on Spoken Languages Technologies for Under-resourced languages ; https://hal.archives-ouvertes.fr/hal-01843405 ; International Workshop on Spoken Languages Technologies for Under-resourced languages, May 2014, St Petersburg, Russia (2014)
|
|
BASE
|
|
Show details
|
|
|
|