W6691770337

• Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression

  2025 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis

  0

  citations
• Chunked Attention-Based Encoder-Decoder Model for Streaming Speech Recognition

  2024 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis

  10

  citations
• On Language Model Integration for RNN Transducer Based Speech Recognition

  2022 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis Open access cited by 1 patent

  18

  citations
• Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition

  2021 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis

  29

  citations
• Exploring A Zero-Order Direct Hmm Based on Latent Attention for Automatic Speech Recognition

  2020 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis

  5

  citations
• The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment

  2020 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis

  47

  citations
• How Much Self-Attention Do We Needƒ Trading Attention for Feed-Forward Layers

  2020 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis cited by 2 patents

  4

  citations

7 results