PhD Candidate in Speech & Audio Deepfake Detection

Aalto University; Espoo; Hybrid; EUR 32,000 - 38,000; Full time

Benefits offered by this job

Hybrid work model

International collaboration

Open science environment

Professional development opportunities

Job summary

Aalto University in Espoo, Finland, invites applications for a Doctoral Researcher in Speech and Language Technology within the COWAMA project. You will detect generated audio content from multiple sources, work with a Postdoctoral Researcher on robustness, evaluation, and generalization, and publish in top venues.

The role offers a hybrid work model, access to top computing resources, and collaboration with international experts.

Qualifications

• A master's degree, or near completion, in speech or audio processing, ML, signal processing, CS, EE, or related field.
• Strong interest in doctoral research on audio deepfake detection, watermarking, source tracing, and generative AI.
• Good programming skills, preferably Python and modern ML tools.
• Basic knowledge of deep learning, signal processing, speech/audio processing, or statistical ML.
• Interest in working with speech/audio datasets, detector models, generative audio models, and evaluation.
• Motivation to publish scientific articles and contribute to open-source and reproducible research.
• Ability to work independently and collaboratively in an international research environment.
• Fluency in English is required; Finnish language is not required.

Responsibilities

• Develop methods for detecting authenticity and origin of speech and audio content from multiple models and watermarking methods.
• Create datasets of diverse real and generated speech and audio from different models and watermarking methods.
• Adapt and improve detector baselines for multi-objective detection of deepfakes, origin, and watermark ID.
• Develop explainable and localized detection methods for watermark and deepfake attribution.
• Study robustness against signal-processing, resynthesis, adversarial, and downstream processing.
• Publish research in leading journals/conferences and contribute to open-source releases.

Skills

Python

Machine learning

Deep learning

Signal processing

Speech processing

Education

Master's degree in related field

Job description

Aalto University in Espoo, Finland, invites applications for a Doctoral Researcher in Speech and Language Technology within the COWAMA project. You will detect generated audio content from multiple sources, work with a Postdoctoral Researcher on robustness, evaluation, and generalization, and publish in top venues.

The role offers a hybrid work model, access to top computing resources, and collaboration with international experts.