Speech/Audio enhancement DSP R&D Engineer

About Synaptics:
Synaptics is the pioneer and leader of the human interface revolution, bringing innovative and intuitive user experiences to intelligent devices. Synaptics' broad portfolio of touch, display, biometrics, voice, audio, and multimedia products is built on the company's rich R&D, extensive IP and dependable supply chain capabilities. With solutions designed for mobile, PC, smart home, and automotive industries, Synaptics combines ease of use, functionality and aesthetics to enable products that help make our digital lives more productive, secure and enjoyable. (NASDAQ: SYNA ) www.synaptics.com .

Job Scope:

We are looking for an outstanding candidate with experience in audio Digital Signal Processing and Machine Learning for working in the field of audio analysis and enhancement, for improving VoIP and ASR applications. The successful candidate will join the audio R&D team and be responsible for doing research and prototyping of advanced DSP algorithms for single and multichannel audio processing for challenging multi-source and far-field scenarios.

Job Responsibilities:

  • Do research on state-of-art in the field of audio signal processing
  • Design new algorithms and benchmark existing techniques in the field of audio multichannel and speech signal processing
  • Write technical documents on algorithm analysis
  • Design objective evaluations, create collaterals, tools for analysis and other support material needed for the productization
  • Collaborate with the SW and FW team for the productization, verification and testing of the new developed algorithms
  • Collaborate with the DSP and PAE for the technological transfer of new feature products.

Job Qualifications:

We are looking for an individual with a strong background in audio digital signal processing and experience in how such processing is implemented in products or systems and ultimately how they translate into an end user experience. A proven track record in developing algorithms for voice/speech processing, either through academic work or industry work is required. Experience in multichannel signal processing, such as Acoustic Echo Cancellation, Beamforming and Blind Source Separation is also desired.

Necessary requirements:
  • MSc or PhD in machine learning, audio signal processing, speech processing or statistics;
  • Proficient programming in C/C++, shell scripting, Matlab/Python;
  • Proven track record of publications in the fields of speech and audio DSP;
  • Good verbal and written communication skills;
  • Enthusiasm and self-commitment;
  • Excellent critical thinking.

Desired skills:
  • Experience with multichannel audio signal processing for speech enhancement or source separation
  • Knowledge of Latex, Linux and software for audio analysis;
  • Prior experience in the design of audio applications for real-world products;
  • Experience with deep learning software and toolboxes;
  • Experience with real-time signal processing;
  • Ability in problem analysis and troubleshooting;
  • Knowledge of audio quality benchmarking tools and metrics.



Back to top