1-Apply machine learning and signal processing techniques in developing our multilingual language identification, speech recognition, audio hashing and sound classification algorithms to production.
2-Training with massive amounts of data with fewer labeled data points, deploying models in servers and resource constrained edge devices.
1-Master or PhD degree in computer science, signal processing, speech re related machine learning field or equivalent practical experience.
2-Familiar with commonly used deep learning and machine learning models.
3-Understanding of digital signal processing, especially adaptive filter, non-linear processing and automatic gain control.
4-Speech recognition background, familiar with acoustic, language modeling and semi-/self supervised learning techniques.
5-Develop and optimize machine learning models for on-device applications in terms of accuracy, computation complexity, model sizes and power consumption.
6-Publications at peer-reviewed speech related conferences.