Toa Payoh - Speech Scientist (Research Engineer)
JOB DESIGNATION
Speech Scientist/ Research Engineer
SCOPE OF RESPONSIBILITIES- Conduct research and product development in voice & speech signal processing. Provide core algorithms using microphone array for speech enhancement and recognition.
- Contribute towards voice-based product development for applications such as acoustic event detection, speaker recognition and speaker diarization.
- Use machine learning and AI technologies for new feature development and existing feature enhancement in area of speech signal processing.
- DSP algorithm design in C/C++, Python, Tensorflow and Matlab.
- Maintain and update product software releases.
- Strong background in voice signal processing, including adaptive filters, speech enhancement, microphone array, noise reduction, acoustic echo cancellation (AEC).
- Familiar with AI algorithms and architectures with reference to their various applications to speech signal processing and applications.
- Knowledge of using speech processing toolkits (Kaldi/ESPnet/SpeechBrian) and deep learning toolkits (PyTorch/Tensorflow).
- 2+ years experiences in algorithm design & implementation.
- A fast learner and keen to learn new methods for developing their prototypes.
- Experience in industrial product design is a plus.
- For Speech Scientist position, candidates with PhD in Electronics/Computer Science Engineering related disciplines or Master’s degree with 3+ years of relevant experience is preferred.
- For Research Engineer position, candidates with Master’s degree in Electronics/Computer Science Engineering related disciplines or Bachelor’s degree with 2+ years of relevant experience is preferred.
ORGANIZATION
Fortemedia Singapore Pte Ltd
LOCATION
Singapore Office
Fortemedia Singapore Pte. Ltd.
#06-27, DUO Tower,3 Fraser Street, Singapore 189352
REPORTING RELATIONSHIP
Report to the Singapore R&D Team Leader
COMPANY BACKGROUND
Fortemedia, Inc., a global company headquartered in the Silicon Valley with operations and offices in Asia, develops software and semi-conductor products that provide advanced voice processing capabilities to enhance human-to-human and human-to-machine voice communication.
The company pioneered Small Array Microphone (SAM®) voice processing technologies. The application of this technology in mobile-phone communications allowed NTT DoCoMo to launch the world's first mobile phone with dual-microphone array speech processing, the RakuRaku III, in 2006.
Well recognized as a technology leader, Fortemedia's ASIC devices and solutions with advanced voice processing technologies, SAM, SAMSoft®, and ForteVoice® , have been widely deployed in numerous commercial systems, devices, and applications.Fortemedia has filed more than 200 patents worldwide with over 75 patents issued.