Internship on Audio Processing and Machine Learning

Position Summary

The Music Technology team at Sony Group Corporation is looking for Research Interns who are passionate about machine learning for audio signal processing. Our mission is to research and develop novel technologies for various Sony Group products and for scientific publication. The technologies developed during the internship will also have the potential to be applied to music and film production workflows in entertainment studios around the world. The working language is English, and our team is composed of members from a wide variety of countries.

Responsibilities

As a Research Intern, you will investigate and apply novel algorithms that combine audio signal processing and machine learning techniques in areas such as music generation, music editing, music attribution analysis, source separation, audio restoration, audio effects manipulation, representation learning for music and audio effects processing, and AI-assisted post-production for music, film, or game audio.

You are expected to implement and optimize these algorithms by applying your research, coding, and problem-solving skills. You will be supported in your efforts by having access to state-of-the-art resources at Sony and a unique and extensive catalog of music data.
Based in Tokyo, you will also have the opportunity to collaborate with other Sony Group Corporation teams and Sony Business Groups such as Sony Music, Sony Pictures, and Sony Interactive Entertainment.

Required Qualifications

• Enrolled in a PhD or MSc program in CS, EE, applied mathematics, or a related field.
• Record of relevant publications, internship experiences, or relevant projects.
• Expertise in audio signal analysis, processing, and feature extraction.
• Experience cleaning, manipulating, and analyzing audio data.
• Proven knowledge of machine learning, including architecture design and training/testing methodologies.
• Proven coding expertise with Python and experience with relevant machine learning tools (e.g. PyTorch, Slurm, Streamlit, etc.).

Preferred qualifications

• Experience as an intern at a research laboratory
• Record of relevant academic publications in topics such as music, audio, or speech
• Evidence of projects (academic/industrial/personal) related to music, audio, or speech
• Interest in music/audio.

Required Skills:

Audio Signal Processing, Deep Learning

Optional Skills: