1 citations · 1 across the 3 of their papers we have counts for
3 papers
cs.CL2023★ 1 cited
End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis
Can Cui, Imran Ahamad Sheikh, Mostafa Sadeghi +1
We present an end-to-end multichannel speaker-attributed automatic speech recognition (MC-SA-ASR) system that combines a Conformer-based encoder with multi-frame crosschannel atten…
cs.CV2023
Unsupervised speech enhancement with diffusion-based generative models
Berné Nortier, Mostafa Sadeghi, Romain Serizel
Recently, conditional score-based diffusion models have gained significant attention in the field of supervised speech enhancement, yielding state-of-the-art performance. However,…
cs.CV2023
Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder
Mostafa Sadeghi, Romain Serizel
In this paper, we address the unsupervised speech enhancement problem based on recurrent variational autoencoder (RVAE). This approach offers promising generalization performance o…