Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Program
-
Field
- Education
- Business
- Computer Science
- Psychology
- Arts and Literature
- Social Sciences
- Medical Sciences
- Biology
- Design
- Engineering
- Humanities
- Law
- Electrical Engineering
- Environment
- Sports and Recreation
- Earth Sciences
- Science
- Statistics
- Chemistry
- Linguistics
- Mathematics
- Philosophy
- Physics
- 13 more »
- « less
-
realistic downstream processing. Your role and goals As the Doctoral Researcher, you will take primary responsibility for detecting generated audio content from multiple sources , and work jointly
-
authenticity of generated and watermarked audio data, improving content-based audio watermarking, and evaluating robustness against removal, spoofing, adversarial attacks, and realistic downstream processing
-
, who leads the Speech Synthesis research group at Aalto University. The group works on deep generative models for speech and audio, speech synthesis, differentiable signal processing, deepfake
-
Speech Synthesis research group at Aalto University. The group works on deep generative models for speech and audio, speech synthesis, differentiable signal processing, deepfake detection, and
-
enhancements Software development of new algorithmic audio processing solutions including the existing areas mentioned above and additionally including state of the art audio codecs, audibility and
-
activities Software development of new algorithmic audio processing solutions including the existing areas mentioned above and additionally including state of the art audio codecs, audibility and
-
and multisensory XR at the intersection of acoustics, signal processing, XR, and human perception. You will develop and evaluate physics-based and data-driven audio rendering methods within the
-
systems and/or software applications to assist in the operations of a large-scale, audio digitization and streaming project for obsolete media. 3. *Maintain, calibrate and operate equipment according to
-
and Multimodal Systems Audio Capture, Processing, and Sensing Audio Modeling and Synthesis ; Multimodal Content Generation The successful candidate will be expected to establish an active
-
; demonstrated expertise in deep learning, preferably as applied to audio; and traditional signal processing. PREFERRED : Computational expertise: Experience with Pytorch, use of high-performance computing