• Refine your search:
  • 
    Keyword:
    
    • Computation and Language cs.CL (4)
    • FOS Computer and information sciences (4)
    • Audio and Speech Processing eess.AS (2)
    • FOS Electrical engineering, electronic engineering, information engineering (2)
    • Machine Learning cs.LG (2)
    • Sound cs.SD (2)
    • 68T10 (1)
    • I.2.7 (1)
  • 
    Creator / Publisher:
    
    • Bapna, Ankur (4)
    • Zhang, Yu (4)
    • Cherry, Colin (2)
    • Conneau, Alexis (2)
    • Jia, Ye (2)
    • Johnson, Melvin (2)
    • Khanuja, Simran (2)
    • Riesa, Jason (2)
    • Auli, Michael (1)
    • Axelrod, Vera (1)
    •   more
  • 
    Year:
    
    • 2022 (3)
    • 2021 (1)
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access

Search in the Catalogues and Directories

All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year Sort by creator [A → Z]' creator [Z → A]' publishing year ↑ (asc)' publishing year ↓ (desc)' title [A → Z]' title [Z → A]' Simple Search Hits 1 – 4 of 4 1 XTREME-S: Evaluating Cross-lingual Speech Representations ... Conneau, Alexis; Bapna, Ankur; Zhang, Yu. - : arXiv, 2022 BASE Show details 2 mSLAM: Massively multilingual joint pre-training for speech and text ... Bapna, Ankur; Cherry, Colin; Zhang, Yu. - : arXiv, 2022 BASE Show details 3 MAESTRO: Matched Speech Text Representations through Modality Matching ... Chen, Zhehuai; Zhang, Yu; Rosenberg, Andrew. - : arXiv, 2022 BASE Show details 4 Joint Unsupervised and Supervised Training for Multilingual ASR ... Bai, Junwen; Li, Bo; Zhang, Yu; Bapna, Ankur; Siddhartha, Nikhil; Sim, Khe Chai; Sainath, Tara N.. - : arXiv, 2021 Abstract: Self-supervised training has shown promising gains in pretraining models and facilitating the downstream finetuning for speech recognition, like multilingual ASR. Most existing methods adopt a 2-stage scheme where the self-supervised loss is optimized in the first pretraining stage, and the standard supervised finetuning resumes in the second stage. In this paper, we propose an end-to-end (E2E) Joint Unsupervised and Supervised Training (JUST) method to combine the supervised RNN-T loss and the self-supervised contrastive and masked language modeling (MLM) losses. We validate its performance on the public dataset Multilingual LibriSpeech (MLS), which includes 8 languages and is extremely imbalanced. On MLS, we explore (1) JUST trained from scratch, and (2) JUST finetuned from a pretrained checkpoint. Experiments show that JUST can consistently outperform other existing state-of-the-art methods, and beat the monolingual baseline by a significant margin, demonstrating JUST's capability of handling low-resource ... Keyword: Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Machine Learning cs.LG; Sound cs.SD URL: https://arxiv.org/abs/2111.08137 https://dx.doi.org/10.48550/arxiv.2111.08137 BASE Hide details

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 0 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 0 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 0 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 0 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 0 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 4 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0