Picture for Mostafa Sadeghi

Mostafa Sadeghi

MULTISPEECH

Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications

Mar 11, 2024
Figure 1 for Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications
Figure 2 for Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications
Figure 3 for Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications
Figure 4 for Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications
Viaarxiv icon

Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge

Add code
Feb 02, 2024
Viaarxiv icon

End-to-end Joint Rich and Normalized ASR with a limited amount of rich training data

Add code
Nov 29, 2023
Viaarxiv icon

End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis

Oct 16, 2023
Viaarxiv icon

Unsupervised speech enhancement with diffusion-based generative models

Add code
Sep 19, 2023
Figure 1 for Unsupervised speech enhancement with diffusion-based generative models
Viaarxiv icon

Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder

Add code
Sep 19, 2023
Figure 1 for Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder
Viaarxiv icon

Diffusion-based speech enhancement with a weighted generative-supervised learning loss

Sep 19, 2023
Viaarxiv icon

The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement

Jul 07, 2023
Figure 1 for The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement
Figure 2 for The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement
Figure 3 for The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement
Viaarxiv icon

Weighted variance variational autoencoder for speech enhancement

Add code
Nov 02, 2022
Figure 1 for Weighted variance variational autoencoder for speech enhancement
Figure 2 for Weighted variance variational autoencoder for speech enhancement
Viaarxiv icon

Audio-visual speech enhancement with a deep Kalman filter generative model

Add code
Nov 02, 2022
Figure 1 for Audio-visual speech enhancement with a deep Kalman filter generative model
Figure 2 for Audio-visual speech enhancement with a deep Kalman filter generative model
Figure 3 for Audio-visual speech enhancement with a deep Kalman filter generative model
Viaarxiv icon