Chiori Hori

Chiori Hori
  • Biography

    Prior to joining MERL in 2015, Chiori spent 8 years at Japan's National Institute of Information and Communication Technology (NICT). Prior to that, she researched at Carnegie Mellon and the NTT Communication Science Laboratories. She was the research manager of Spoken Language Communication Laboratory of NICT from 2012. Chiori's work has focused on speech summarization/translation, spoken dialog technologies, and standardization of communication protocols for speech interfaces at ITU-T and ASTAP. She has been an editorial board of "Computer Speech and Language" since 2016.

  • News & Events

    •  EVENT   MERL leads organization of dialog technology challenges and associated workshop
      Date: Sunday, December 10, 2017
      MERL Contacts: Bret Harsham; John Hershey; Chiori Hori; Takaaki Hori
      Location: Hyatt Regency, Long Beach, CA
      Research Areas: Multimedia, Speech & Audio
      Brief
      • MERL researcher Chiori Hori led the organization of the 6th edition of the Dialog System Technology Challenges (DSTC6). This year's edition of DSTC is split into three tracks: End-to-End Goal Oriented Dialog Learning, End-to-End Conversation Modeling, and Dialogue Breakdown Detection. A total of 23 teams from all over the world competed in the various tracks, and will meet at the Hyatt Regency in Long Beach, CA, USA on December 10 to present their results at a dedicated workshop colocated with NIPS 2017.

        MERL's Speech and Audio Team and Mitsubishi Electric Corporation jointly submitted a set of systems to the End-to-End Conversation Modeling Track, obtaining the best rank among 19 submissions in terms of objective metrics.
    •  
    •  TALK   Generative Model-Based Text-to-Speech Synthesis
      Date & Time: Wednesday, February 1, 2017; 12:00-13:00
      Speaker: Dr. Heiga ZEN, Google
      MERL Host: Chiori Hori
      Research Areas: Multimedia, Speech & Audio
      Brief
      • Recent progress in generative modeling has improved the naturalness of synthesized speech significantly. In this talk I will summarize these generative model-based approaches for speech synthesis such as WaveNet, a deep generative model of raw audio waveforms. We show that WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems.
        See https://deepmind.com/blog/wavenet-generative-model-raw-audio/ for further details.
    •  

    See All News & Events for Chiori
  • Research Highlights

  • Internships with Chiori

    • MM1151: Scene-Aware Dialog Technology

      MERL is looking for an intern to work on fundamental research in the area of scene-aware dialog technologies by combining end-to-end dialog and video scene understanding technologies. The intern will collaborate with MERL researchers to derive and implement new models, conduct experiments, and prepare results for high impact publication. The ideal candidate would be a senior Ph.D. student with experience in one or more of visual question answering, video captioning/description, end-to-end conversation modeling and natural language processing including practical machine learning algorithms with related programming skills. The duration of the internship is expected to be 3-6 months. Positions are available throughout 2018.

    See All Internships at MERL
  • MERL Publications

    See All Publications for Chiori
  • MERL Issued Patents

    • Title: "Method and System for Role Dependent Context Sensitive Spoken and Textual Language Understanding with Neural Networks"
      Inventors: Hori, Chiori; Hori, Takaaki; Watanabe, Shinji; Hershey, John R.
      Patent No.: 9,842,106
      Issue Date: Dec 12, 2017
    See All Patents for MERL