activity
20172021
most citedWeighted Speech Distortion Losses for Neural-network-based Real-time Speech Enhancement

17 citations · 34 across the 4 of their papers we have counts for

collaborators
Showing eess.ASShow all

9 papers · 1 filter

eess.AS2021

Low complexity online convolutional beamforming

Sebastian Braun, Ivan Tashev

Convolutional beamformers integrate the multichannel linear prediction model into beamformers, which provide good performance and optimality for joint dereverberation and noise red…

eess.AS2021

On training targets for noise-robust voice activity detection

Sebastian Braun, Ivan Tashev

The task of voice activity detection (VAD) is an often required module in various speech processing, analysis and classification tasks. While state-of-the-art neural network based…

eess.AS2021

Towards efficient models for real-time deep noise suppression

Sebastian Braun, Hannes Gamper, Chandan K. A. Reddy +1

With recent research advancements, deep learning models are becoming attractive and powerful choices for speech enhancement in real-time applications. While state-of-the-art models…

eess.AS2020

A consolidated view of loss functions for supervised deep learning-based speech enhancement

Sebastian Braun, Ivan Tashev

Deep learning-based speech enhancement for real-time applications recently made large advancements. Due to the lack of a tractable perceptual optimization target, many myths around…

eess.AS2020

Data augmentation and loss normalization for deep noise suppression

Sebastian Braun, Ivan Tashev

Speech enhancement using neural networks is recently receiving large attention in research and being integrated in commercial devices and applications. In this work, we investigate…

eess.AS202017 cited

Weighted Speech Distortion Losses for Neural-network-based Real-time Speech Enhancement

Yangyang Xia, Sebastian Braun, Chandan K. A. Reddy +3

This paper investigates several aspects of training a RNN (recurrent neural network) that impact the objective and subjective quality of enhanced speech for real-time single-channe…