ML Engineer - Speech Synthesis

WorldWide
LOVO
ago
remote fulltime Enhancement TTS

Work with a world class team of engineers and scientists, including the authors of WaveGlow, Mellotron, and Flowtron, to solve some of the most complex problems involving speech synthesis systems today, including:

  • Low-data DIY voice cloning
  • Speaker generation
  • Voice conversion
  • Dynamic emotion generation
  • Non-verbal speech synthesis
  • Singing synthesis and more.

Main Responsibilities

  • Research and Experiment with the latest speech synthesis technology and models
  • Review and Apply the latest papers published

Basic Qualifications

  • Bachelors in AI and Deep-learning related fields
  • Strong background knowledge of Tensorflow, Pytorch framework
  • Experience working with Multi-GPU and high-performing computing.
  • Experience building and implementing a machine-learning / deep-learning model
  • Quick and precise understanding and application of the latest papers
  • English proficiency

Portfolio

  • Format: pdf, github, etc.
  • Must include: List and timeline of the key projects you had participated in, Platform and language, a summary of key ideas, your specific roles and contribution to the projects

Preferred Qualifications

  • Published in major journals and conferences in topics relevant to speech synthesis.
  • Experience building speech synthesis systems from scratch.
  • MS or PhD in Computer Science, Data Science, Math, Physics, or related quantitative field.

Find out more about our cultures and who we are - https://bit.ly/LOVOHire

How to apply

Please send your cv to [email protected]