Postdoctoral Researcher: AI Audio Watermarking & Speech

Aalto University; Espoo; Hybrid; EUR 43,000 - 51,000; Full time

Benefits offered by this job

Hybrid work model

Open science & open-source releases

Excellent computing resources

International collaboration network

Job summary

Aalto University’s Department of Information and Communications Engineering invites applications for a Postdoctoral Researcher in Speech and Language Technology. The role focuses on content-based watermarking for AI-generated audio within the COWAMA project, reporting to Assistant Professor Lauri Juvela on a cutting-edge, open-science driven initiative.

You will work on deep learning methods for watermarking, robustness evaluation, and open-source software releases, collaborating with

Qualifications

• PhD in speech/audio processing, ML, signal processing, CS or related field.
• Strong experience with deep learning and generative models.
• Programming skills for ML research, preferably Python and DL frameworks.

Responsibilities

• Develop content-based audio watermarking methods for generated speech, music, and audio.
• Design detection and perceptual quality measures for perceptually acceptable deviations.
• Integrate watermarking into deep audio generative models and diffusion models.

Skills

Deep learning

Generative models

Python

ML frameworks

Education

Doctoral degree or near completion

Tools

PyTorch

TensorFlow

Job description

Aalto University’s Department of Information and Communications Engineering invites applications for a Postdoctoral Researcher in Speech and Language Technology. The role focuses on content-based watermarking for AI-generated audio within the COWAMA project, reporting to Assistant Professor Lauri Juvela on a cutting-edge, open-science driven initiative.

You will work on deep learning methods for watermarking, robustness evaluation, and open-source software releases, collaborating with