Speech Recognition Research Scientist - Kaldi, Speech Research, Voice Interface Design, Application Prototyping, Speech SDK, API, Acoustic Modeling, Language Modeling, Machine Learning, C++, NLP, DSP - Pasadena, CA
As a Speech Recognition Research Engineer, you’ll be working on several proprietary and stealth projects in the audio space. Your work will encompass the whole scope of application development, including speech research, voice interface design, application prototyping, and development of our proprietary speech recognition engine.
- Evaluate speech experiences using curated and live application data
- Integrate state of the art acoustic modeling, language modeling, and high-performance search methods into our on-device speech recognition engine
- Help build and support integration of the speech SDK into existing and new products
- Help build and support the API for our developer ecosystems
- Implement new speech experiences for in-development products
- Build Speech Recognition Systems, preferably in Kaldi
- PhD (Preferred), M.Sc. in Computer Science, Electrical Engineering or Physics
- Experience with Kaldi
- Experience with data-driven statistical or machine learning methods
- Enjoys a highly collaborative environment with minimal supervision
Nice to have:
- Experience with automatic speech recognition and/or natural language processing systems
- Familiarity with linguistic phonetics
- High proficiency in C++
- Knowledge of basic digital signal processing techniques for audio.
- Experience with software engineering best practices including unit testing, continuous integration, and source control.