Zobrazeno 1 - 10
of 404
pro vyhledávání: '"Sadeghi, Mostafa"'
Past studies on end-to-end meeting transcription have focused on model architecture and have mostly been evaluated on simulated meeting data. We present a novel study aiming to optimize the use of a Speaker-Attributed ASR (SA-ASR) system in real-life
Externí odkaz:
http://arxiv.org/abs/2403.06570
Autor:
Leglaive, Simon, Fraticelli, Matthieu, ElGhazaly, Hend, Borne, Léonie, Sadeghi, Mostafa, Wisdom, Scott, Pariente, Manuel, Hershey, John R., Pressnitzer, Daniel, Barker, Jon P.
Supervised models for speech enhancement are trained using artificially generated mixtures of clean speech and noise signals. However, the synthetic training conditions may not accurately reflect real-world conditions encountered during testing. This
Externí odkaz:
http://arxiv.org/abs/2402.01413
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 attention and a speaker-attributed Transformer-based decoder. To the best o
Externí odkaz:
http://arxiv.org/abs/2310.10106
Autor:
Sadeghi, Mostafa, Serizel, Romain
In this paper, we address the unsupervised speech enhancement problem based on recurrent variational autoencoder (RVAE). This approach offers promising generalization performance over the supervised counterpart. Nevertheless, the involved iterative v
Externí odkaz:
http://arxiv.org/abs/2309.10439
Diffusion-based generative models have recently gained attention in speech enhancement (SE), providing an alternative to conventional supervised methods. These models transform clean speech training samples into Gaussian noise centered at noisy speec
Externí odkaz:
http://arxiv.org/abs/2309.10457
Recently, conditional score-based diffusion models have gained significant attention in the field of supervised speech enhancement, yielding state-of-the-art performance. However, these methods may face challenges when generalising to unseen conditio
Externí odkaz:
http://arxiv.org/abs/2309.10450
Autor:
Leglaive, Simon, Borne, Léonie, Tzinis, Efthymios, Sadeghi, Mostafa, Fraticelli, Matthieu, Wisdom, Scott, Pariente, Manuel, Pressnitzer, Daniel, Hershey, John R.
Publikováno v:
The 7th International Workshop on Speech Processing in Everyday Environments (CHiME), Dublin, Ireland, 2023
Supervised speech enhancement models are trained using artificially generated mixtures of clean speech and noise signals, which may not match real-world recording conditions at test time. This mismatch can lead to poor performance if the test domain
Externí odkaz:
http://arxiv.org/abs/2307.03533
Autor:
Sadeghi, Mostafa, Serizel, Romain
Unsupervised speech enhancement based on variational autoencoders has shown promising performance compared with the commonly used supervised methods. This approach involves the use of a pre-trained deep speech prior along with a parametric noise mode
Externí odkaz:
http://arxiv.org/abs/2211.02728
We address speech enhancement based on variational autoencoders, which involves learning a speech prior distribution in the time-frequency (TF) domain. A zero-mean complex-valued Gaussian distribution is usually assumed for the generative model, wher
Externí odkaz:
http://arxiv.org/abs/2211.00990
Deep latent variable generative models based on variational autoencoder (VAE) have shown promising performance for audiovisual speech enhancement (AVSE). The underlying idea is to learn a VAEbased audiovisual prior distribution for clean speech data,
Externí odkaz:
http://arxiv.org/abs/2211.00988