Meta AR/VR Job | Software Engineer Intern, Speech and Audio Render Algorithms
Job（岗位）: Software Engineer Intern, Speech and Audio Render Algorithms
Type（岗位类型）: Research
Citys（岗位城市）: Redmond, WA
Date（发布日期）: Before 2021-12-14
Summary（岗位介绍）
The XR Audio team at Facebook is helping people around the world come together and connect through world-class Augmented and Virtual Reality hardware and software. We are developing the future of AR and VR, bringing products to consumers that transform entertainment and social experiences.
These roles are focused on developing the next generation of speech and audio enhancement algorithms for wearables in various acoustic environments. In particular we welcome PhD students in Electrical Engineering, Computer Science, Physics, or similar fields, with a strong background in digital signal processing, spatial sound render, adaptive system identification, sound source localization & separation, and machine learning with application to speech and audio enhancement.
Qualifications（岗位要求）
Demonstrated ability in algorithm development for speech & audio render.
Currently has, or is in the process of obtaining, a PhD degree in the field of Electrical Engineering, Computer Science, Physics, or related fields.
2+ years of experience in algorithm development in fields of speech enhancement, spatial rendering, and hardware prototyping.
2+ years experience with MATLAB and Python.
Demonstrated experience via an internship, work experience, research publication, or widely used contributions to open source projects.
Interpersonal skills: cross-group and cross-culture collaboration.
Must obtain work authorization in the country of employment at the time of hire and maintain ongoing work authorization during employment .
Description（岗位职责）
Develop next-generation speech enhancement and audio render algorithms for wearable devices.
MATLAB/Python prototyping of real-time audio processing pipelines.
Extensive evaluation of algorithms through standard objective metrics.
Compare different methods for spatial audio render and acoustic simulations. Suggest improvements and prototype ideas for evaluation.
Additional Requirements（额外要求）
Intent to return to degree-program after the completion of the internship/co-op
Experience with PyTorch or TensorFlow.
2+ years experience with C or C++.
Good understanding of acoustics, sound field modeling and decomposition/synthesis.
Experience with machine learning based speech enhancement (Noise Reduction, Sound Source Localization, Beamforming, etc.).
Experience in developing algorithms on compute-constrained platforms such as mobile SoCs.
Proven track record of achieving significant results as demonstrated by first-authored publications (e.g., ICASSP, InterSpeech, IWAENC, WASPAA).
Good listening skills and able to detect audio artefacts with experience in conducting perceptual audio quality tests.
Familiarity with perceptual audio concepts especially for spatial audio playback.
Familiarity with binauralization and panning concepts for surround sound playback.
Understanding or experience in common audio processing blocks such as Dynamic Range Compression, Automatic Gain Control and Limiters.
