11 papers
Ensemble-Based Perceptual Audio Quality Assessment with Confidence Intervals
Pablo M. Delgado, Andreas Brendel, Konstantin Schmidt +1
Objective audio quality metrics typically provide point estimates, whereas listening tests yield score distributions from which mean opinion scores (MOS), confidence intervals (CIs…
PADP: Perceptual Audio Data Perturbation for Probing Perception Awareness in Audio Quality Models
Guanxin Jiang, Andreas Brendel, Pablo M. Delgado +1
This paper presents a collection of audio transforms that introduce perceptually irrelevant distortions and demonstrates their use as perceptual stress tests for audio quality mode…
Discriminative Flow Matching: Beyond Time-Conditioning in Generative Restoration via Flow-State Representations
Shrishti Saha Shetu, Emanuël A. P. Habets, Andreas Brendel
Existing Conditional Flow Matching (CFM) formulations describe transport progress using an explicit interpolation coordinate, commonly interpreted as time, assuming that a single g…
Room Impulse Response Completion Using Signal-Prediction Diffusion Models Conditioned on Simulated Early Reflections
Zeyu Xu, Andreas Brendel, Albert G. Prinn +1
Room impulse responses (RIRs) are fundamental to audio data augmentation, acoustic signal processing, and immersive audio rendering. While geometric simulators such as the image so…
Robust Online Overdetermined Independent Vector Analysis Based on Bilinear Decomposition
Kang Chen, Xianrui Wang, Yichen Yang +6
Online blind source separation is essential for both speech communication and human-machine interaction. Among existing approaches, overdetermined independent vector analysis (Over…
DeePAQ: A Perceptual Audio Quality Metric Based On Foundational Models and Weakly Supervised Learning
Guanxin Jiang, Andreas Brendel, Pablo M. Delgado +1
This paper presents the Deep learning-based Perceptual Audio Quality metric (DeePAQ) for evaluating general audio quality. Our approach leverages metric learning together with the…
GAN-Based Multi-Microphone Spatial Target Speaker Extraction
Shrishti Saha Shetu, Emanuël A. P. Habets, Andreas Brendel
Spatial target speaker extraction isolates a desired speaker's voice in multi-speaker environments using spatial information, such as the direction of arrival (DoA). Although recen…
Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancement
Shrishti Saha Shetu, Emanuël A. P. Habets, Andreas Brendel
Generative speech enhancement methods based on generative adversarial networks (GANs) and diffusion models have shown promising results in various speech enhancement tasks. However…
GAN-Based Speech Enhancement for Low SNR Using Latent Feature Conditioning
Shrishti Saha Shetu, Emanuël A. P. Habets, Andreas Brendel
Enhancing speech quality under adverse SNR conditions remains a significant challenge for discriminative deep neural network (DNN)-based approaches. In this work, we propose DisCoG…
Comparative Analysis Of Discriminative Deep Learning-Based Noise Reduction Methods In Low SNR Scenarios
Shrishti Saha Shetu, Emanuël A. P. Habets, Andreas Brendel
In this study, we conduct a comparative analysis of deep learning-based noise reduction methods in low signal-to-noise ratio (SNR) scenarios. Our investigation primarily focuses on…
Blind Acoustic Parameter Estimation Through Task-Agnostic Embeddings Using Latent Approximations
Philipp Götz, Cagdas Tuna, Andreas Brendel +2
We present a method for blind acoustic parameter estimation from single-channel reverberant speech. The method is structured into three stages. In the first stage, a variational au…