Picture for Robin Scheibler

Robin Scheibler

Universal Score-based Speech Enhancement with High Content Preservation

Add code
Jun 18, 2024
Viaarxiv icon

URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement

Add code
Jun 07, 2024
Viaarxiv icon

TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch

Add code
Oct 27, 2023
Figure 1 for TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Figure 2 for TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Figure 3 for TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Figure 4 for TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Viaarxiv icon

Neural Diarization with Non-autoregressive Intermediate Attractors

Add code
Mar 13, 2023
Figure 1 for Neural Diarization with Non-autoregressive Intermediate Attractors
Figure 2 for Neural Diarization with Non-autoregressive Intermediate Attractors
Figure 3 for Neural Diarization with Non-autoregressive Intermediate Attractors
Figure 4 for Neural Diarization with Non-autoregressive Intermediate Attractors
Viaarxiv icon

Diffusion-based Generative Speech Source Separation

Add code
Nov 02, 2022
Figure 1 for Diffusion-based Generative Speech Source Separation
Figure 2 for Diffusion-based Generative Speech Source Separation
Figure 3 for Diffusion-based Generative Speech Source Separation
Figure 4 for Diffusion-based Generative Speech Source Separation
Viaarxiv icon

ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

Add code
Jul 19, 2022
Figure 1 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Figure 2 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Figure 3 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Figure 4 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Viaarxiv icon

End-to-End Multi-speaker ASR with Independent Vector Analysis

Add code
Apr 01, 2022
Figure 1 for End-to-End Multi-speaker ASR with Independent Vector Analysis
Figure 2 for End-to-End Multi-speaker ASR with Independent Vector Analysis
Figure 3 for End-to-End Multi-speaker ASR with Independent Vector Analysis
Figure 4 for End-to-End Multi-speaker ASR with Independent Vector Analysis
Viaarxiv icon

Spatial Loss for Unsupervised Multi-channel Source Separation

Add code
Apr 01, 2022
Figure 1 for Spatial Loss for Unsupervised Multi-channel Source Separation
Figure 2 for Spatial Loss for Unsupervised Multi-channel Source Separation
Figure 3 for Spatial Loss for Unsupervised Multi-channel Source Separation
Figure 4 for Spatial Loss for Unsupervised Multi-channel Source Separation
Viaarxiv icon

MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition

Add code
Feb 17, 2022
Figure 1 for MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition
Figure 2 for MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition
Figure 3 for MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition
Figure 4 for MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition
Viaarxiv icon

Low-Memory End-to-End Training for Iterative Joint Speech Dereverberation and Separation with A Neural Source Model

Add code
Oct 13, 2021
Figure 1 for Low-Memory End-to-End Training for Iterative Joint Speech Dereverberation and Separation with A Neural Source Model
Figure 2 for Low-Memory End-to-End Training for Iterative Joint Speech Dereverberation and Separation with A Neural Source Model
Figure 3 for Low-Memory End-to-End Training for Iterative Joint Speech Dereverberation and Separation with A Neural Source Model
Figure 4 for Low-Memory End-to-End Training for Iterative Joint Speech Dereverberation and Separation with A Neural Source Model
Viaarxiv icon