K. Hirose

Publications517
h-index27
Citations4,654
Highly Influential Citations214
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • N. Minematsu
  • 470 Publications • 3,492 Citations
  • H. Fujisaki
  • 216 Publications • 3,138 Citations
  • M. I. Molla
  • 84 Publications • 793 Citations
  • D. Saito
  • 132 Publications • 1,052 Citations
  • Publications
  • Influence
Foreword
  • K. Hirose
  • Computer Science
    Journal of Physiology-Paris
  • 30 June 2011
View on Elsevier
Analysis of voice fundamental frequency contours for declarative sentences of Japanese
TLDR
Analysis of natural utterances of various declarative sentences of Japanese revealed that the model can generate close approximations to observed F0 contours from a set of discrete commands and a small number of parameters.
View via Publisher
WFST-Based Grapheme-to-Phoneme Conversion: Open Source tools for Alignment, Model-Building and Decoding
This paper introduces a new open source, WFST-based toolkit for Grapheme-toPhoneme conversion. The toolkit is efficient, accurate and currently supports a range of features including EM sequence…
View on ACL
Phonetisaurus: Exploring grapheme-to-phoneme conversion with joint n-gram models in the WFST framework
TLDR
Phonetisaurus is introduced, a fully-functional, flexible, open-source, BSD-licensed G2P conversion toolkit, which leverages the OpenFst library and achieves new state-of-the-art performance via ensemble methods combining RnnLMs and n-gram based models.
View on Cambridge Press
Failure transitions for joint n-gram models and G2p conversion
TLDR
Two novel algorithms are proposed, which extend the work from [1] and enable the use of failure-transitions with joint n-gram models via the WFST framework, and are available as part of the open-source, BSD-licensed Phonetisaurus G2P toolkit.
View Paper
Improving WFST-based G2P Conversion with Alignment Constraints and RNNLM N-best Rescoring
This work introduces a modified WFST-based multiple to multiple EM-driven alignment algorithm for Graphemeto-Phoneme (G2P) conversion, and preliminary experimental results applying a Recurrent Neural…
View Paper
Filled pauses as cues to the complexity of upcoming phrases for native and non-native listeners
View via Publisher
Single-Mixture Audio Source Separation by Subspace Decomposition of Hilbert Spectrum
TLDR
A novel technique is developed to separate the audio sources from a single mixture based on decomposing the Hilbert spectrum of the mixed signal into independent source subspaces and the inverse transformation is applied.
View on IEEE
Tone nucleus modeling for Chinese lexical tone recognition
View via Publisher
Teaching the pronunciation of Japanese double-mora phonemes using speech recognition technology
View via Publisher
...
...