• Principal Speech Scientist

    Location US-MA-Burlington
    Job ID
    1-36137
    Category
    Research & Development - Software Engineer (Development or Programming)
    Pos. Type
    Full Time
  • Company Overview

    At Nuance, we empower people with the ability to seamlessly interact with their connected devices and the digital world around them.  We are creating a world where technology thinks and acts the way people do by designing the most human, natural, and intuitive ways of interacting with technology.

     

    Our nimble technology uses analytics and advanced algorithms to transform the inanimate into animate and reduce complicated processes into simple ones.

     

    Join our Mobile team…intelligent systems now ready for the road. We are passionate about developing intelligent interfaces that enable people to talk to their cars, phones, devices, and other smart “things”.

     

    Job Summary

    Summary

     

    Work as part of Nuance’s ASR technology research team to conduct research into all aspects of speech recognition algorithms with the aim of optimizing accuracy with a focus on Automotive applications. This will include research into algorithms and advanced modeling techniques to increase robustness to various acoustic conditions encountered in real-world data and the creation of “world English” acoustic and language models.

     

    Principal Duties and Responsibilities

     

    Provide experimental and theoretical analysis of speech recognition problems.
    Formulate new algorithms, create research tools, and design and implement experiments to verify new algorithms.
    Optimize the accuracy of speech recognition systems on challenging real-world data.
    Work with team members to build and deliver acoustic and language models for Nuance Automotive products.
    Follow developments in speech recognition algorithms to keep our research state-of-the-art.

    Knowledge, skills and Qualifications

     

    Education: Ph.D. or Master degree in speech recognition, machine learning, or engineering

    Minimum years of work experience:  10

    Required skills:

     

    A good understanding of machine learning algorithms including deep learning.
    In-depth understanding of speech recognition algorithms including neural network based acoustic and language modelling.
    Experience building acoustic and language models.
    Python and shell scripting in a UNIX environment.
    Demonstrated ability to conduct novel research in speech recognition algorithms.
    Good written and oral communications skills.
    Ability to take initiative, but also follow a plan and work well as part of a team.
    Ability to work successfully with minimum supervision as part of diverse teams and provide mentorship to less experienced researchers.

     

    Preferred skills:
    Good analytical and diagnostic skills.
    Experience of running large scale experiments in a Sun Grid Engine environment.
    Experience with C/C++.

    Options

    Sorry the Share function is not working properly at this moment. Please refresh the page and try again later.
    Share on your newsfeed

    Connect With Us!

    Not ready to apply? Connect with us for general consideration.