Search Results - "Kokubo, Hiroaki"

  • Showing 1 - 12 results of 12
Refine Results
  1. 1

    Efficient Corpus Creation Method for NLU Using Interview with Probing Questions by Shima, Kazuaki, Homma, Takeshi, Motohashi, Masataka, Ikeshita, Rintaro, Kokubo, Hiroaki, Obuchi, Yasunari, She, Jinhua

    “…This paper presents an efficient method to build a corpus to train natural language understanding (NLU) modules. Conventional corpus creation methods involve a…”
    Get full text
    Journal Article
  2. 2
  3. 3

    Compressing the factoring table and performing garbage collection on unusable word hypotheses in a continuous speech recognition system by Kokubo, Hiroaki, Hayashi, Teruaki, Yamamoto, Hirofumi, Kikui, Genichiro

    “…We have investigated methods for reducing the number of word hypotheses registered in the word graph and the amount of memory used by the factoring tables for…”
    Get full text
    Journal Article
  4. 4

    Out-of-vocabulary word recognition using a hierarchical language model based on multiple Markov models by Yamamoto, Hirofumi, Kokubo, Hiroaki, Kikui, Genichiro, Ogawa, Yoshihiko, Sagisaka, Yoshinori

    “…In this paper we propose a language model to solve the issue of task‐dependent out‐of‐vocabulary words in speech recognition. Language model adaptation is a…”
    Get full text
    Journal Article
  5. 5

    Robust speech recognition for car environment noise by Kokubo, Hiroaki, Amano, Akio, Hataoka, Nobuo

    “…A method for handling noise in a car information machine incorporating speech recognition middleware and having a SuperH (SH) Micon as its platform is…”
    Get full text
    Journal Article
  6. 6
  7. 7

    Beamforming array technique with clustered multichannel noise covariance matrix for mechanical noise reduction by Togami, Masahito, Sumiyoshi, Takashi, Obuchi, Yasunari, Kawaguchi, Yohei, Kokubo, Hiroaki

    “…In this paper, we propose a novel multichannel noise reduction method for a mechanical noise with a time-variant impulse response. The mechanical noise source…”
    Get full text
    Conference Proceeding
  8. 8

    Subband beamformer combined with time-frequency ICA for extraction of target source under reverberant environments by Togami, Masahito, Kawaguchi, Yohei, Kokubo, Hiroaki, Obuchi, Yasunari

    “…We propose a novel beamforming method that is complementarily combined with the time-frequency domain independent component analysis (TF-ICA). Under…”
    Get full text
    Conference Proceeding Journal Article
  9. 9

    Embedded Julius: Continuous Speech Recognition Software for Microprocessor by Kokubo, Hiroaki, Hataoka, Nobuo, Lee, Akinobu, Kawahara, Tatsuya

    “…To expand CSR (continuous speech recognition) software to the mobile environmental use, we have developed embedded version of "Julius". Julius is open source…”
    Get full text
    Conference Proceeding
  10. 10

    Real-Time Continuous Speech Recognition System on SH-4A Microprocessor by Kokubo, H., Hataoka, N., Lee, A., Kawahara, T., Shikano, K.

    “…To expand CSR (continuous speech recognition) software to the mobile environmental use, we have developed embedded version of Julius (embedded Julius). Julius…”
    Get full text
    Conference Proceeding
  11. 11

    Embedded Julius on T-Engine Platform by Hataoka, N., Kokubo, H., Lee, A., Kawahara, T., Shikano, K.

    “…In this paper, we report implemental results of an embedded version of Julius. We used T-Enginetrade as a hardware platform which has a SuperH microprocessor…”
    Get full text
    Conference Proceeding
  12. 12

    Out-of-vocabulary word recognition with a hierarchical doubly Markov language model by Kokubo, H., Yamamoto, H., Ogawa, Y., Sagisaka, Y., Kikui, G.

    “…We describe a novel language model for task-dependent out-of-vocabulary (OOV) words. OOV words, such as personal names and place names in a new task, can make…”
    Get full text
    Conference Proceeding