| 1 |
Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 2 |
A Configurable Multilingual Model is All You Need to Recognize All Languages ...
|
|
|
|
Abstract:
Multilingual automatic speech recognition (ASR) models have shown great promise in recent years because of the simplified model training and deployment process. Conventional methods either train a universal multilingual model without taking any language information or with a 1-hot language ID (LID) vector to guide the recognition of the target language. In practice, the user can be prompted to pre-select several languages he/she can speak. The multilingual model without LID cannot well utilize the language information set by the user while the multilingual model with LID can only handle one pre-selected language. In this paper, we propose a novel configurable multilingual model (CMM) which is trained only once but can be configured as different models based on users' choices by extracting language-specific modules together with a universal model from the trained CMM. Particularly, a single CMM can be deployed to any user scenario where the users can pre-select any combination of languages. Trained with 75K ...
|
|
Keyword:
Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Sound cs.SD
|
|
URL: https://arxiv.org/abs/2107.05876
https://dx.doi.org/10.48550/arxiv.2107.05876
|
|
BASE
|
|
Hide details
|
|
|
| 3 |
Self-Supervised Learning for speech recognition with Intermediate layer supervision ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Factorized Neural Transducer for Efficient Language Model Adaptation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Production de la parole en réponse à de multiples perturbations du feedback auditif
|
|
|
|
In: Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole ; https://hal.archives-ouvertes.fr/hal-02798560 ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole, Jun 2020, Nancy, France. pp.370-378 (2020)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Complexity patterns underlying speech production activity
|
|
|
|
In: ISSP 2020 ; https://hal.archives-ouvertes.fr/hal-03100430 ; ISSP 2020, Dec 2020, Online, United States (2020)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Speech production in response to multiple perturbations of auditory feedback
|
|
|
|
In: ISSP 2020 ; https://hal.archives-ouvertes.fr/hal-03100466 ; ISSP 2020, Dec 2020, Online, United States (2020)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Manipulating verbal interaction via artificial agents to study inter-speaker coordination
|
|
|
|
In: Social cognition in humans and robots ; https://hal.archives-ouvertes.fr/hal-01874505 ; Social cognition in humans and robots, Sep 2018, Hamburg, Germany ; https://www.socsmcs.eu/conference2018 (2018)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
End-to-End Attention based Text-Dependent Speaker Verification ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Improved training for online end-to-end speech recognition systems ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
