Bret Harsham

Bret Harsham
  • Biography

    Before joining MERL in 2001, Bret worked at Dragon Systems on handheld and automotive speech products. At MERL, he works on research projects in the area of speech and multimodal applications, with a focus on effectiveness and usability. Past research projects have included work on multi-user touch interfaces and the safety & usability of in-car speech applications.

  • News & Events

    •  EVENT   MERL leads organization of dialog technology challenges and associated workshop
      Date: Sunday, December 10, 2017
      MERL Contacts: Bret Harsham; Chiori Hori; Takaaki Hori
      Location: Hyatt Regency, Long Beach, CA
      Research Area: Speech & Audio
      • 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.
    •  NEWS   MERL's breakthrough speech separation technology featured in Mitsubishi Electric Corporation's Annual R&D Open House
      Date: May 24, 2017
      Where: Tokyo, Japan
      MERL Contacts: Bret Harsham; Jonathan Le Roux
      Research Areas: Speech & Audio
      • Mitsubishi Electric Corporation announced that it has created the world's first technology that separates in real time the simultaneous speech of multiple unknown speakers recorded with a single microphone. It's a key step towards building machines that can interact in noisy environments, in the same way that humans can have meaningful conversations in the presence of many other conversations. In tests, the simultaneous speeches of two and three people were separated with up to 90 and 80 percent accuracy, respectively. The novel technology, which was realized with Mitsubishi Electric's proprietary "Deep Clustering" method based on artificial intelligence (AI), is expected to contribute to more intelligible voice communications and more accurate automatic speech recognition. A characteristic feature of this approach is its versatility, in the sense that voices can be separated regardless of their language or the gender of the speakers. A live speech separation demonstration that took place on May 24 in Tokyo, Japan, was widely covered by the Japanese media, with reports by three of the main Japanese TV stations and multiple articles in print and online newspapers. The technology is based on recent research by MERL's Speech and Audio team.
        Mitsubishi Electric Corporation Press Release
        MERL Deep Clustering Demo

        Media Coverage:

        Fuji TV, News, "Minna no Mirai" (Japanese)
        The Nikkei (Japanese)
        Nikkei Technology Online (Japanese)
        Sankei Biz (Japanese)
        EE Times Japan (Japanese)
        ITpro (Japanese)
        Nikkan Sports (Japanese)
        Nikkan Kogyo Shimbun (Japanese)
        Dempa Shimbun (Japanese)
        Il Sole 24 Ore (Italian)
        IEEE Spectrum (English)

    See All News & Events for Bret
  • MERL Publications

    See All Publications for Bret
  • MERL Issued Patents

    • Title: "Method for using a Multi-Scale Recurrent Neural Network with Pretraining for Spoken Language Understanding Tasks"
      Inventors: Watanabe, Shinji; Luan, Yi; Harsham, Bret A.
      Patent No.: 9,607,616
      Issue Date: Mar 28, 2017
    • Title: "Actions Prediction for Hypothetical Driving Conditions"
      Inventors: Harsham, Bret A.; Hershey, John R.; Le Roux, Jonathan; Nikovski, Daniel N.; Esenther, Alan W.
      Patent No.: 9,434,389
      Issue Date: Sep 6, 2016
    • Title: "Method and System for Autonomously Delivering Information to Drivers"
      Inventors: Nikovski, Daniel N.; Harsham, Bret A.; Hershey, John R.; Brinkman, Dirk
      Patent No.: 9,305,306
      Issue Date: Apr 5, 2016
    • Title: "Determining Word Sequence Constraints for Low Cognitive Speech Recognition"
      Inventors: Harsham, Bret A.; Hershey, John R.
      Patent No.: 9,196,246
      Issue Date: Nov 24, 2015
    • Title: "Method and System for Dynamically Adapting user Interfaces in Vehicle Navigation Systems to Minimize Interaction Complexity"
      Inventors: Nikovski, Daniel N.; Hershey, John R.; Harsham, Bret A.; Le Roux, Jonathan
      Patent No.: 9,170,119
      Issue Date: Oct 27, 2015
    • Title: "System and Method for Recognizing Speech"
      Inventors: Harsham, Bret A.; Hershey, John R.
      Patent No.: 9,159,317
      Issue Date: Oct 13, 2015
    • Title: "Method for Indexing for Retrieving Documents Using Particles"
      Inventors: Ramakrishnan, Bhiksha R.; Gouvea, Evandro B.; Harsham, Bret A.; Schmidt-Nielsen, Bent K.; Weinberg, Garrett L.
      Patent No.: 8,229,921
      Issue Date: Jul 24, 2012
    • Title: "Method for Interacting With Users of Speech Recognition Systems"
      Inventors: Schmidt-Nielsen, Bent K.; Weinberg, Garrett L.; Ramakrishnan, Bhiksha R.; Harsham, Bret A.
      Patent No.: 7,917,368
      Issue Date: Mar 29, 2011
    See All Patents for MERL