1 citations · 3 across the 13 of their papers we have counts for
15 papers
CochlearMark: Audio Watermarking via Phase Locked Auditory Nerve Representations
Qin Liu, Strahinja Nikolic, Milos Cernak
Modern audio watermarks achieve strong robustness with learned encoder-decoder models, but their behavior under new processing is established empirically. CochlearMark is introduce…
StreamMark: A Deep Learning-Based Semi-Fragile Audio Watermarking for Proactive Deepfake Detection
Zhentao Liu, Milos Cernak
The rapid advancement of generative AI has made it increasingly challenging to distinguish between deepfake audio and authentic human speech. To overcome the limitations of passive…
Calibration-Reasoning Framework for Descriptive Speech Quality Assessment
Elizaveta Kostenok, Mathieu Salzmann, Milos Cernak
Explainable speech quality assessment requires moving beyond Mean Opinion Scores (MOS) to analyze underlying perceptual dimensions. To address this, we introduce a novel post-train…
An Interpretable, Controllable Time-Varying IIR Denoiser for On-Device Assistive Hearing
Riccardo Rota, Kiril Ratmanski, Jozef Coldenhoff +1
We present TVBC (Time-Varying Biquad Cascade), an interpretable, low-latency speech enhancement model for real-time, on-device assistive hearing. A lightweight neural controller pr…
Zimtohrli: An Efficient Psychoacoustic Audio Similarity Metric
Jyrki Alakuijala, Martin Bruse, Sami Boukortt +2
This paper introduces Zimtohrli, a novel, full-reference audio similarity metric designed for efficient and perceptually accurate quality assessment. In an era dominated by computa…
Shortcut Flow Matching for Speech Enhancement: Step-Invariant flows via single stage training
Naisong Zhou, Saisamarth Rajesh Phaye, Milos Cernak +4
Diffusion-based generative models have achieved state-of-the-art performance for perceptual quality in speech enhancement (SE). However, their iterative nature requires numerous Ne…
Low-latency Assistive Audio Enhancement for Neurodivergent People
Alexander Popescu, Rosie Frost, Milos Cernak
Neurodivergent people frequently experience decreased sound tolerance, with estimates suggesting it affects 50-70% of this population. This heightened sensitivity can provoke react…
DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration
Sanberk Serbest, Tijana Stojkovic, Milos Cernak +1
In this work, we propose a full-band real-time speech enhancement system with GAN-based stochastic regeneration. Predictive models focus on estimating the mean of the target distri…
Model as Loss: A Self-Consistent Training Paradigm
Saisamarth Rajesh Phaye, Milos Cernak, Andrew Harper
Conventional methods for speech enhancement rely on handcrafted loss functions (e.g., time or frequency domain losses) or deep feature losses (e.g., using WavLM or wav2vec), which…
Diffusion-based Speech Enhancement with Schrödinger Bridge and Symmetric Noise Schedule
Siyi Wang, Siyi Liu, Andrew Harper +3
Recently, diffusion-based generative models have demonstrated remarkable performance in speech enhancement tasks. However, these methods still encounter challenges, including the l…
Semi-intrusive audio evaluation: Casting non-intrusive assessment as a multi-modal text prediction task
Jozef Coldenhoff, Milos Cernak
Human perception has the unique ability to focus on specific events in a mixture of signals--a challenging task for existing non-intrusive assessment methods. In this work, we intr…
OpenACE: An Open Benchmark for Evaluating Audio Coding Performance
Jozef Coldenhoff, Niclas Granqvist, Milos Cernak
Audio and speech coding lack unified evaluation and open-source testing. Many candidate systems were evaluated on proprietary, non-reproducible, or small data, and machine learning…
On real-time multi-stage speech enhancement systems
Lingjun Meng, Jozef Coldenhoff, Paul Kendrick +4
Recently, multi-stage systems have stood out among deep learning-based speech enhancement methods. However, these systems are always high in complexity, requiring millions of param…
Cluster-based pruning techniques for audio data
Boris Bergsma, Marta Brzezinska, Oleg V. Yazyev +1
Deep learning models have become widely adopted in various domains, but their performance heavily relies on a vast amount of data. Datasets often contain a large number of irreleva…
Multi-Channel MOSRA: Mean Opinion Score and Room Acoustics Estimation Using Simulated Data and a Teacher Model
Jozef Coldenhoff, Andrew Harper, Paul Kendrick +2
Previous methods for predicting room acoustic parameters and speech quality metrics have focused on the single-channel case, where room acoustics and Mean Opinion Score (MOS) are p…