8 citations · 32 across the 14 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
eess.AS2023★ 4 cited
Privacy-oriented manipulation of speaker representations
Francisco Teixeira, Alberto Abad, Bhiksha Raj +1
Speaker embeddings are ubiquitous, with applications ranging from speaker recognition and diarization to speech synthesis and voice anonymisation. The amount of information held by…
eess.AS2023★ 1 cited
Memory-augmented conformer for improved end-to-end long-form ASR
Carlos Carvalho, Alberto Abad
Conformers have recently been proposed as a promising modelling approach for automatic speech recognition (ASR), outperforming recurrent neural network-based approaches and transfo…