Search Results - Tuske, Zoltan

Refine Results
  1. 1
    Advancing RNN Transducer Technology for Speech Recognition

    Advancing RNN Transducer Technology for Speech Recognition by Saon, George, Tuske, Zoltan, Bolanos, Daniel, Kingsbury, Brian

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  2. 2
    Sequence Noise Injected Training for End-to-end Speech Recognition

    Sequence Noise Injected Training for End-to-end Speech Recognition by Saon, George, Tuske, Zoltan, Audhkhasi, Kartik, Kingsbury, Brian

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  3. 3
    RNN Transducer Models for Spoken Language Understanding

    RNN Transducer Models for Spoken Language Understanding by Thomas, Samuel, Kuo, Hong-Kwang J., Saon, George, Tuske, Zoltan, Kingsbury, Brian, Kurata, Gakuto, Kons, Zvi, Hoory, Ron

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  4. 4
    Improving End-to-end Models for Set Prediction in Spoken Language Understanding

    Improving End-to-end Models for Set Prediction in Spoken Language Understanding by Kuo, Hong-Kwang J., Tuske, Zoltan, Thomas, Samuel, Kingsbury, Brian, Saon, George

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  5. 5
    End-to-End Spoken Language Understanding Using Transformer Networks and Self-Supervised Pre-Trained Features

    End-to-End Spoken Language Understanding Using Transformer Networks and Self-Supervised Pre-Trained Features by Morais, Edmilson, Kuo, Hong-Kwang J., Thomas, Samuel, Tuske, Zoltan, Kingsbury, Brian

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  6. 6
    Multilingual MRASTA features for low-resource keyword search and speech recognition systems

    Multilingual MRASTA features for low-resource keyword search and speech recognition systems by Tuske, Zoltan, Nolden, David, Schluter, Ralf, Ney, Hermann

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  7. 7
    Alignment-Length Synchronous Decoding for RNN Transducer

    Alignment-Length Synchronous Decoding for RNN Transducer by Saon, George, Tuske, Zoltan, Audhkhasi, Kartik

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  8. 8
    Non-stationary feature extraction for automatic speech recognition

    Non-stationary feature extraction for automatic speech recognition by Tuske, Zoltan, Golik, Pavel, Schluter, Ralf, Drepper, Friedhelm R.

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  9. 9
    Acoustic Modeling of Speech Waveform Based on Multi-Resolution, Neural Network Signal Processing

    Acoustic Modeling of Speech Waveform Based on Multi-Resolution, Neural Network Signal Processing by Tuske, Zoltan, Schluter, Ralf, Ney, Hermann

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  10. 10
    Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables

    Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables by Tuske, Zoltan, Tahir, Muhammad Ali, Schluter, Ralf, Ney, Hermann

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  11. 11
    Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions

    Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions by Tuske, Zoltan, Pinto, Joel, Willett, Daniel, Schluter, Ralf

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  12. 12
    SADA: Saudi Audio Dataset for Arabic

    SADA: Saudi Audio Dataset for Arabic by Alharbi, Sadeen, Alowisheq, Areeb, Tuske, Zoltan, Darwish, Kareem, Alrajeh, Abdullah, Alrowithi, Abdulmajeed, Tamran, Aljawharah Bin, Ibrahim, Asma, Aloraini, Raghad, Alnajim, Raneem, Alkahtani, Ranya, Almuasaad, Renad, Alrasheed, Sara, Alsubaie, Shaykhah, Alonaizan, Yaser

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  13. 13
    Deep hierarchical bottleneck MRASTA features for LVCSR

    Deep hierarchical bottleneck MRASTA features for LVCSR by Tuske, Zoltan, Schluter, Ralf, Ney, Hermann

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  14. 14
    English Broadcast News Speech Recognition by Humans and Machines

    English Broadcast News Speech Recognition by Humans and Machines by Thomas, Samuel, Suzuki, Masayuki, Huang, Yinghui, Kurata, Gakuto, Tuske, Zoltan, Saon, George, Kingsbury, Brian, Picheny, Michael, Dibert, Tom, Kaiser-Schatzlein, Alice, Samko, Bern

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  15. 15
    Investigation on log-linear interpolation of multi-domain neural network language model

    Investigation on log-linear interpolation of multi-domain neural network language model by Tuske, Zoltan, Irie, Kazuki, Schluter, Ralf, Ney, Hermann

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  16. 16
    The RWTH English lecture recognition system

    The RWTH English lecture recognition system by Wiesler, Simon, Irie, Kazuki, Tuske, Zoltan, Schluter, Ralf, Ney, Hermann

    Request full text
    Conference Proceeding
    Save to List
    Saved in:
  17. 17
    Improved Recognition of Spontaneous Hungarian Speech-Morphological and Acoustic Modeling Techniques for a Less Resourced Task

    Improved Recognition of Spontaneous Hungarian Speech-Morphological and Acoustic Modeling Techniques for a Less Resourced Task by Mihajlik, P, Tuske, Z, Tarján, B, Németh, B, Fegyó, T

    Get full text
    Items that this one cites
    Items that cite this one
    Article
    Save to List
    Saved in:
  18. 18
    Weak Alignment Supervision from Hybrid Model Improves End-to-end ASR

    Weak Alignment Supervision from Hybrid Model Improves End-to-end ASR by Jiang, Jintao, Gao, Yingbo, Tuske, Zoltan

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  19. 19
    Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASR

    Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASR by Jiang, Jintao, Gao, Yingbo, Zeineldeen, Mohammad, Tuske, Zoltan

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  20. 20
    Reducing Exposure Bias in Training Recurrent Neural Network Transducers

    Reducing Exposure Bias in Training Recurrent Neural Network Transducers by Cui, Xiaodong, Kingsbury, Brian, Saon, George, Haws, David, Tuske, Zoltan

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:

Search Tools: