• Refine your search:
  • 
    Keyword:
    
    • Audio and Speech Processing eess.AS (2)
    • FOS Electrical engineering, electronic engineering, information engineering (2)
    • Signal Processing eess.SP (1)
  • 
    Creator / Publisher:
    
    • Chen, Berlin (2)
    • Weng, Shi-Yan (2)
    • Chao, Fu-An (1)
    • Chiu, Shih-Hsuan (1)
    • Lo, Tien-Hong (1)
    • Sung, Yao-Ting (1)
  • 
    Year
  • 
    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 – 2 of 2 1 The NTNU Taiwanese ASR System for Formosa Speech Recognition Challenge 2020 ... Chao, Fu-An; Lo, Tien-Hong; Weng, Shi-Yan. - : arXiv, 2021 BASE Show details 2 Effective Decoder Masking for Transformer Based End-to-End Speech Recognition ... Weng, Shi-Yan; Chen, Berlin. - : arXiv, 2020 Abstract: The attention-based encoder-decoder modeling paradigm has achieved promising results on a variety of speech processing tasks like automatic speech recognition (ASR), text-to-speech (TTS) and among others. This paradigm takes advantage of the generalization ability of neural networks to learn a direct mapping from an input sequence to an output sequence, without recourse to prior knowledge such as audio-text alignments or pronunciation lexicons. However, ASR models stemming from this paradigm are prone to overfitting, especially when the training data is limited. Inspired by SpecAugment and BERT-like masked language modeling, we propose in the paper a decoder masking based training approach for end-to-end (E2E) ASR models. During the training phase we randomly replace some portions of the decoder's historical text input with the symbol [mask], in order to encourage the decoder to robustly output a correct token even when parts of its decoding history are masked or corrupted. The proposed approach is ... : More extensions and experiments are under exploration ... Keyword: Audio and Speech Processing eess.AS; FOS Electrical engineering, electronic engineering, information engineering URL: https://arxiv.org/abs/2010.14764 https://dx.doi.org/10.48550/arxiv.2010.14764 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 2 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0