328 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Fraunhofer Institute for Integrated CircuitsDE22 papers
- Friedrich-Alexander-Universität Erlangen-NürnbergDE12 papers
- Academia SinicaTW1 paper
- Aston UniversityGB1 paper
- Bar-Ilan UniversityIL1 paper
- Google (United States)US1 paper
- Harvey Mudd CollegeUS1 paper
- Ingegneria dei Sistemi (United Kingdom)GB1 paper
- Johannes Kepler University of LinzAT1 paper
- Laboratoire des Sciences du Numérique de NantesFR1 paper
- London Rebuilding SocietyGB1 paper
- Massachusetts Institute of TechnologyUS1 paper
23 papers · 1 filter
Robust Speech Activity Detection in the Presence of Singing Voice
Philipp Grundhuber, Mhd Modar Halimeh, Martin Strauß +1
Speech Activity Detection (SAD) systems often misclassify singing as speech, leading to degraded performance in applications such as dialogue enhancement and automatic speech recog…
UBGAN: Enhancing Coded Speech with Blind and Guided Bandwidth Extension
Kishan Gupta, Srikanth Korse, Andreas Brendel +2
In practical application of speech codecs, a multitude of factors such as the quality of the radio connection, limiting hardware or required user experience necessitate trade-offs…
Perceptual Audio Coding: A 40-Year Historical Perspective
Jürgen Herre, Schuyler Quackenbush, Minje Kim +1
In the history of audio and acoustic signal processing, perceptual audio coding has certainly excelled as a bright success story by its ubiquitous deployment in virtually all digit…
Low-Resource Text-to-Speech Synthesis Using Noise-Augmented Training of ForwardTacotron
Kishor Kayyar Lakshminarayana, Frank Zalkow, Christian Dittmar +2
In recent years, several text-to-speech systems have been proposed to synthesize natural speech in zero-shot, few-shot, and low-resource scenarios. However, these methods typically…
Towards Improved Objective Perceptual Audio Quality Assessment -- Part 1: A Novel Data-Driven Cognitive Model
Pablo M. Delgado, Jürgen Herre
Efficient audio quality assessment is vital for streamlining audio codec development. Objective assessment tools have been developed over time to algorithmically predict quality ra…
FlowMAC: Conditional Flow Matching for Audio Coding at Low Bit Rates
Nicola Pia, Martin Strauss, Markus Multrus +1
This paper introduces FlowMAC, a novel neural audio codec for high-quality general audio compression at low bit rates based on conditional flow matching (CFM). FlowMAC jointly lear…
SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement
Martin Strauss, Nicola Pia, Nagashree K. S. Rao +1
This paper proposes SEFGAN, a Deep Neural Network (DNN) combining maximum likelihood training and Generative Adversarial Networks (GANs) for efficient speech enhancement (SE). For…
Can we still use PEAQ? A Performance Analysis of the ITU Standard for the Objective Assessment of Perceived Audio Quality
Pablo M. Delgado, Jürgen Herre
The Perceptual Evaluation of Audio Quality (PEAQ) method as described in the International Telecommunication Union (ITU) recommendation ITU-R BS.1387 has been widely used for compu…
Objective Assessment of Spatial Audio Quality using Directional Loudness Maps
Pablo M. Delgado, Jürgen Herre
This work introduces a feature extracted from stereophonic/binaural audio signals aiming to represent a measure of perceived quality degradation in processed spatial auditory scene…
An Analysis Method for Metric-Level Switching in Beat Tracking
Ching-Yu Chiu, Meinard Müller, Matthew E. P. Davies +2
For expressive music, the tempo may change over time, posing challenges to tracking the beats by an automatic model. The model may first tap to the correct tempo, but then may fail…
Dialogue Enhancement and Listening Effort in Broadcast Audio: A Multimodal Evaluation
Matteo Torcoli, Thomas Robotham, Emanuël A. P. Habets
Dialogue enhancement (DE) plays a vital role in broadcasting, enabling the personalization of the relative level between foreground speech and background music and effects. DE has…
Blind Reverberation Time Estimation in Dynamic Acoustic Conditions
Philipp Götz, Cagdas Tuna, Andreas Walther +1
The estimation of reverberation time from real-world signals plays a central role in a wide range of applications. In many scenarios, acoustic conditions change over time which in…
Signal-Aware Direction-of-Arrival Estimation Using Attention Mechanisms
Wolfgang Mack, Julian Wechsler, Emanuël A. P. Habets
The direction-of-arrival (DOA) of sound sources is an essential acoustic parameter used, e.g., for multi-channel speech enhancement or source tracking. Complex acoustic scenarios c…
Objective Measures of Perceptual Audio Quality Reviewed: An Evaluation of Their Application Domain Dependence
Matteo Torcoli, Thorsten Kastner, Jürgen Herre
Over the past few decades, computational methods have been developed to estimate perceptual audio quality. These methods, also referred to as objective quality measures, are usuall…
Controlling the Remixing of Separated Dialogue with a Non-Intrusive Quality Estimate
Matteo Torcoli, Jouni Paulus, Thorsten Kastner +1
Remixing separated audio sources trades off interferer attenuation against the amount of audible deteriorations. This paper proposes a non-intrusive audio quality estimation method…
A Flow-Based Neural Network for Time Domain Speech Enhancement
Martin Strauss, Bernd Edler
Speech enhancement involves the distinction of a target speech signal from an intrusive background. Although generative approaches using Variational Autoencoders or Generative Adve…
Efficient Training Data Generation for Phase-Based DOA Estimation
Fabian Hübner, Wolfgang Mack, Emanuël A. P. Habets
Deep learning (DL) based direction of arrival (DOA) estimation is an active research topic and currently represents the state-of-the-art. Usually, DL-based DOA estimators are train…
An Empirical Study of Visual Features for DNN based Audio-Visual Speech Enhancement in Multi-talker Environments
Shrishti Saha Shetu, Soumitro Chakrabarty, Emanuël A. P. Habets
Audio-visual speech enhancement (AVSE) methods use both audio and visual features for the task of speech enhancement and the use of visual features has been shown to be particularl…
Multi-scale aggregation of phase information for reducing computational cost of CNN based DOA estimation
Soumitro Chakrabarty, Emanuël A. P. Habets
In a recent work on direction-of-arrival (DOA) estimation of multiple speakers with convolutional neural networks (CNNs), the phase component of short-time Fourier transform (STFT)…
On the difference-to-sum power ratio of speech and wind noise based on the Corcos model
Daniele Mirabilii, Emanuël A. P. Habets
The difference-to-sum power ratio was proposed and used to suppress wind noise under specific acoustic conditions. In this contribution, a general formulation of the difference-to-…
Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained with Noise Signals
Soumitro Chakrabarty, Emanuël A. P. Habets
Supervised learning based methods for source localization, being data driven, can be adapted to different acoustic conditions via training and have been shown to be robust to adver…
Simulating Multi-channel Wind Noise Based on the Corcos Model
Daniele Mirabilii, Emanuël A. P. Habets
A novel multi-channel artificial wind noise generator based on a fluid dynamics model, namely the Corcos model, is proposed. In particular, the model is used to approximate the com…
Classification vs. Regression in Supervised Learning for Single Channel Speaker Count Estimation
Fabian-Robert Stöter, Soumitro Chakrabarty, Bernd Edler +1
The task of estimating the maximum number of concurrent speakers from single channel mixtures is important for various audio-based applications, such as blind source separation, sp…