AI SPEECH ALGORITHM ENGINEER

GloBoths Robotics is a worldwide-leading robotics company dedicated to the design, R&D, production, and sales of commercial service robots with a mission to use robots to improve the efficiency of human production and living. 

Adhering to the business goal of "achieving the commercial success of robots in various fields around the world", GloBoths is committed to promoting the commercialization of the robot industry and creating more value for global users. 

LOCATION

Toront

EMPLOYMENY TYPE

Full-Time

What You’ll Do

  • Responsible for multilingual speech recognition algorithms/speech wake-up/speech synthesis, including acoustic model training and algorithm research, decoder technology research and development, compression and optimization under various low-resource conditions, etc.;

  • Build an algorithm testing and verification platform to evaluate algorithm performance;

  • Combine with cloud service scenarios, promote the implementation of voice technology, closed-loop cloud service voice ecology

  • Responsible for sorting out speech interaction named body recognition, knowledge base and knowledge map, language model, syntax analysis, emotion analysis, text classification, data mining, etc., in catering and delivery scenarios;

  • Responsible for following up the development trend of cutting-edge technologies in the industry and planning research and development work, tracking the development direction of international algorithms and corresponding technologies, and developing selective and rapid prototype systems;

  • Responsible for medium - and long-term technical planning of the company's voice interaction, and building and promoting the voice interaction architecture.

Who You are

  • Bachelor degree or above in computer, electronic information, automation or related field;

  • Rich C/C++, Python programming experience and good coding habits, familiar with Linux system;

  • Data sensitivity, familiar with voice data collection and cleaning;

  • Familiar with signal processing, acoustic model, deep learning model;

  • Experience in speech recognition/wake up or machine learning projects is preferred.

  • No limit on working years;

  • Experience in big data and artificial intelligence is preferred;

  • Good team work and communication skills, expression and ability to work under pressure;

  • Good sense of responsibility and dedication.

  • Familiar with common speech related deep learning frameworks such as Kaldi, Tensorflow, PyTorch etc.