4 papers · 1 filter
PLACE: Positional Latent Adaptation via Conditioned Embeddings for Binaural Audio Generation
Tiernon Riesenmy, You Zhang, Gautam Bhattacharya +1
We present PLACE, a method that extends the pretrained any-to-audio model AudioX for binaural generation from arbitrary combinations of text, video, and optional audio prompts. PLA…
Audio-Visual Speech Separation via Bottleneck Iterative Network
Sidong Zhang, Shiv Shankar, Trang Nguyen +2
Integration of information from non-auditory cues can significantly improve the performance of speech-separation models. Often such models use deep modality-specific networks to ob…
Are Deep Speech Denoising Models Robust to Adversarial Noise?
Will Schwarzer, Neel Chaudhari, Philip S. Thomas +2
Deep noise suppression (DNS) models enjoy widespread use throughout a variety of high-stakes speech applications. However, we show that four recent DNS models can each be reduced t…
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
Yixin Liu, Lie Lu, Jihui Jin +2
The rapid proliferation of generative audio synthesis and editing technologies has raised serious concerns about copyright infringement, data provenance, and the spread of misinfor…