Search Results for author:
Found 3 papers, 2 papers with code
METR: Image Watermarking with Large Number of Unique Messages
Improvements in diffusion models have boosted the quality of image generation, which has led researchers, companies, and creators to focus on improving watermarking algorithms.
Adapting WavLM for Speech Emotion Recognition
Recently, the usage of speech self-supervised models (SSL) for downstream tasks has been drawing a lot of attention.
EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech
In our work, we selected FastSpeech2 as the starting point and proposed a series of modifications for synthesizing emotional speech.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
