Hirokazu Masataki

Artificial Intelligence · 2017

A researcher in the Science corpus: 1 paper; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

Whom Hirokazu Masataki trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

  1. Hank Liao

Papers from Hirokazu Masataki's perspective

Ordered by how strongly the researchers Hirokazu Masataki trusts endorse each paper. Same corpus, a different order for every researcher.

  1. Distilling the Knowledge in a Neural Network (arXiv.org)
  2. Speaker adaptation of context dependent deep neural networks
  3. Learning small-size DNN with output-distribution-based criteria
  4. Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code
  5. Speaker adaptation of neural network acoustic models using i-vectors
  6. KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition
  7. Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models
  8. The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices
  9. Spontaneous Speech Corpus of Japanese (International Conference on Language Resources and Evaluation)
  10. Long Short-Term Memory

Their papers