44 citations · 100 across the 34 of their papers we have counts for
5 papers · 1 filter
Toroidal Probabilistic Spherical Discriminant Analysis
Anna Silnova, Niko Brümmer, Albert Swart +1
In speaker recognition, where speech segments are mapped to embeddings on the unit hypersphere, two scoring back-ends are commonly used, namely cosine scoring and PLDA. We have rec…
Speaker adaptation for Wav2vec2 based dysarthric ASR
Murali Karthick Baskar, Tim Herzig, Diana Nguyen +4
Dysarthric speech recognition has posed major challenges due to lack of training data and heavy mismatch in speaker characteristics. Recent ASR systems have benefited from readily…
Jointly Trained Transformers models for Spoken Language Translation
Hari Krishna Vydana, Martin Karafi'at, Katerina Zmolikova +2
Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from…
How to Improve Your Speaker Embeddings Extractor in Generic Toolkits
Hossein Zeinali, Lukas Burget, Johan Rohdin +2
Recently, speaker embeddings extracted with deep neural networks became the state-of-the-art method for speaker verification. In this paper we aim to facilitate its implementation…
Spoken Pass-Phrase Verification in the i-vector Space
Hossein Zeinali, Lukas Burget, Hossein Sameti +1
The task of spoken pass-phrase verification is to decide whether a test utterance contains the same phrase as given enrollment utterances. Beside other applications, pass-phrase ve…