Vasileios Moschopoulos
YOU?
Author Swipe
View article: Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling
Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling Open
Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing enrol…
View article: Exploring compressibility of transformer based text-to-music (TTM) models
Exploring compressibility of transformer based text-to-music (TTM) models Open
State-of-the art Text-To-Music (TTM) generative AI models are large and require desktop or server class compute, making them infeasible for deployment on mobile phones. This paper presents an analysis of trade-offs between model compressio…
View article: Locality enhanced dynamic biasing and sampling strategies for contextual ASR
Locality enhanced dynamic biasing and sampling strategies for contextual ASR Open
Automatic Speech Recognition (ASR) still face challenges when recognizing time-variant rare-phrases. Contextual biasing (CB) modules bias ASR model towards such contextually-relevant phrases. During training, a list of biasing phrases are …
View article: Lucy-SKG: Learning to Play Rocket League Efficiently Using Deep Reinforcement Learning
Lucy-SKG: Learning to Play Rocket League Efficiently Using Deep Reinforcement Learning Open
A successful tactic that is followed by the scientific community for advancing AI is to treat games as problems, which has been proven to lead to various breakthroughs. We adapt this strategy in order to study Rocket League, a widely popul…