Timo Gerkmann

Hamburg University | UHH · Department of Informatics

Due to their robustness and flexibility, neural-driven beamformers are a popular choice for speech separation in challenging environments with a varying amount of simultaneous speakers alongside noise and reverberation. Time-frequency masks and relative directions of the speakers regarding a fixed spatial grid can be used to estimate the beamformer...

Diffusion models have found great success in generating high quality, natural samples of speech, but their potential for density estimation for speech has so far remained largely unexplored. In this work, we leverage an unconditional diffusion model trained only on clean speech for the assessment of speech quality. We show that the quality of a spe...

Generative speech enhancement has recently shown promising advancements in improving speech quality in noisy environments. Multiple diffusion-based frameworks exist, each employing distinct training objectives and learning techniques. This paper aims at explaining the differences between these frameworks by focusing our investigation on score-based...

Collaborating in a group, whether face-to-face or virtually, involves continuously expressing emotions and interpreting those of other group members. Therefore, understanding group affect is essential to comprehending how groups interact and succeed in collaborative efforts. In this study, we move beyond individual-level affect and investigate grou...

In this paper, we present an unsupervised single-channel method for joint blind dereverberation and room impulse response estimation, based on posterior sampling with diffusion models. We parameter-ize the reverberation operator using a filter with exponential decay for each frequency subband, and iteratively estimate the corresponding parameters a...

This paper presents an unsupervised method for single-channel blind dereverberation and room impulse response (RIR) estimation, called BUDDy. The algorithm is rooted in Bayesian posterior sampling: it combines a likelihood model enforcing fidelity to the reverberant measurement, and an anechoic speech prior implemented by an unconditional diffusion...

Single-channel speech separation is a crucial task for enhancing speech recognition systems in multi-speaker environments. This paper investigates the robustness of state-of-the-art Neural Network models in scenarios where the pitch differences between speakers are minimal. Building on earlier findings by Ditter and Gerkmann, which identified a sig...

We release the EARS (Expressive Anechoic Recordings of Speech) dataset, a high-quality speech dataset comprising 107 speakers from diverse backgrounds, totaling in 100 hours of clean, anechoic speech data. The dataset covers a large range of different speaking styles, including emotional speech, different reading styles, non-verbal sounds, and conv...

To obtain improved speech enhancement models, researchers often focus on increasing performance according to specific instrumental metrics. However, when the same metric is used in a loss function to optimize models, it may be detrimental to aspects that the given metric does not see. The goal of this paper is to illustrate the risk of overfitting...

In this work, we utilize the high-fidelity generation abilities of diffusion models to solve blind JPEG restoration at high compression levels. We propose an elegant modification of the forward stochastic differential equation of diffusion models to adapt them to this restoration task and name our method DriftRec . Comparing DriftRec against an...

In this work, we present a causal speech enhancement system that is designed to handle different types of corruptions. This paper is an extended version of our contribution to the “ICASSP 2023 Speech Signal Improvement Challenge”. The method is based on a generative diffusion model which has been shown to work well in scenarios beyond speech-in-noi...

In this work, we demonstrate that the ptychographic phase problem can be solved in a live fashion during scanning, while data is still being collected. We propose a generally applicable modification of the widespread projection-based algorithms such as Error Reduction (ER) and Difference Map (DM). This novel variant of ptychographic phase retrieval...

Human-robot interaction relies on a noise-robust audio processing module capable of estimating target speech from audio recordings impacted by environmental noise, as well as self-induced noise, so-called ego-noise. While external ambient noise sources vary from environment to environment, ego-noise is mainly caused by the internal motors and joint...

In this paper we present a method for single-channel wind noise reduction using our previously proposed diffusion-based stochastic regeneration model combining predictive and generative modelling. We introduce a non-additive speech in noise model to account for the non-linear deformation of the membrane caused by the wind flow and possible clipping...

We present in this paper an informed single-channel dereverberation method based on conditional generation with diffusion models. With knowledge of the room impulse response, the anechoic utterance is generated via reverse diffusion using a measurement consistency criterion coupled with a neural network that represents the clean speech prior. The p...

Since its inception, the field of deep speech enhancement has been dominated by predictive (discriminative) approaches, such as spectral mapping or masking. Recently, however, novel generative approaches have been applied to speech enhancement, attaining good denoising performance with high subjective quality scores. At the same time, advances in d...

This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information. In particular, we exploit audio-visual embeddings obtained from a self-super\-vised learning model that has been fine-tuned on lipreading. The layer-wise features of its tra...

Speech emotion conversion aims to convert the expressed emotion of a spoken utterance to a target emotion while preserving the lexical information and the speaker's identity. In this work, we specifically focus on in-the-wild emotion conversion where parallel data does not exist, and the problem of disentangling lexical, speaker, and emotion inform...

We propose Audio-Visual Lightweight ITerative model (AVLIT), an effective and lightweight neural network that uses Progressive Learning (PL) to perform audio-visual speech separation in noisy environments. To this end, we adopt the Asynchronous Fully Recurrent Convolutional Neural Network (A-FRCNN), which has shown successful results in audio-only...

In large part due to their implicit semantic modeling, self-supervised learning (SSL) methods have significantly increased the performance of valence recognition in speech emotion recognition (SER) systems. Yet, their large size may often hinder practical implementations. In this work, we take HuBERT as an example of an SSL model and analyze the re...

Supervised masking approaches in the time-frequency domain aim to employ deep neural networks to estimate a multiplicative mask to extract clean speech. This leads to a single estimate for each input without any guarantees or measures of reliability. In this paper, we study the benefits of modeling uncertainty in clean speech estimation. Prediction...

A two-stage lightweight online dereverberation algorithm for hearing devices is presented in this paper. The approach combines a multi-channel multi-frame linear filter with a single-channel single-frame post-filter. Both components rely on power spectral density (PSD) estimates provided by deep neural networks (DNNs). By deriving new metrics analy...

In a multi-channel separation task with multiple speakers, we aim to recover all individual speech signals from the mixture. In contrast to single-channel approaches, which rely on the different spectro-temporal characteristics of the speech signals, multi-channel approaches should additionally utilize the different spatial locations of the sources...

Supervised masking approaches in the time-frequency domain aim to employ deep neural networks to estimate a multiplicative mask to extract clean speech. This leads to a single estimate for each input without any guarantees or measures of reliability. In this paper, we study the benefits of modeling uncertainty in clean speech estimation. Prediction...

Human-robot interaction relies on a noise-robust audio processing module capable of estimating target speech from audio recordings impacted by environmental noise, as well as self-induced noise, so-called ego-noise. While external ambient noise sources vary from environment to environment, ego-noise is mainly caused by the internal motors and joint...

In this paper, we present a scheme for extending deep neural network-based multiplicative maskers to deep subband filters for speech restoration in the time-frequency domain. The resulting method can be generically applied to any deep neural network providing masks in the time-frequency domain, while requiring only few more trainable parameters and...

Recently, score-based generative models have been successfully employed for the task of speech enhancement. A stochastic differential equation is used to model the iterative forward process, where at each step environmental noise and white Gaussian noise are added to the clean speech signal. While in limit the mean of the forward process ends at th...

Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive corruption types or when they are evaluated on mismatched conditions. However, diffusion models suffer from a high...

To train machine learning algorithms to predict emotional expressions in terms of arousal and valence, annotated datasets are needed. However, as different people perceive others' emotional expressions differently, their annotations are subjective. To account for this, annotations are typically collected from multiple annotators and averaged to obt...

In this work, we build upon our previous publication and use diffusion-based generative models for speech enhancement. We present a detailed overview of the diffusion process that is based on a stochastic differential equation and delve into an extensive theoretical examination of its implications. Opposed to usual conditional generation tasks, we...

Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive corruption types or when they are evaluated on mismatched conditions. However, diffusion models suffer from a high...

In a multi-channel separation task with multiple speakers, we aim to recover all individual speech signals from the mixture. In contrast to single-channel approaches, which rely on the different spectro-temporal characteristics of the speech signals, multi-channel approaches should additionally utilize the different spatial locations of the sources...

Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive corruption types or when they are evaluated on mismatched conditions. However, diffusion models suffer from a high...

Single-channel deep speech enhancement approaches often estimate a single multiplicative mask to extract clean speech without a measure of its accuracy. Instead, in this work, we propose to quantify the uncertainty associated with clean speech estimates in neural network-based speech enhancement. Predictive uncertainty is typically categorized into...

In this work, we utilize the high-fidelity generation abilities of diffusion models to solve blind image restoration tasks, using JPEG artifact removal at high compression levels as an example. We propose an elegant modification of the forward stochastic differential equation of diffusion models to adapt them to restoration tasks and name our metho...

Diffusion probabilistic models have been recently used in a variety of tasks, including speech enhancement and synthesis. As a generative approach, diffusion models have been shown to be especially suitable for imputation problems, where missing data is generated based on existing data. Phase retrieval is inherently an imputation problem, where pha...

Diffusion-based generative models have had a high impact on the computer vision and speech processing communities these past years. Besides data generation tasks, they have also been employed for data restoration tasks like speech enhancement and dereverberation. While discriminative models have traditionally been argued to be more powerful e.g. fo...

In a scenario with multiple persons talking simultaneously, the spatial characteristics of the signals are the most distinct feature for extracting the target signal. In this work, we develop a deep joint spatial-spectral non-linear filter that can be steered in an arbitrary target direction. For this we propose a simple and effective conditioning...

p>To train machine learning algorithms to predict emotional expressions in terms of arousal and valence, annotated datasets are needed. However, as different people perceive others’ emotional expressions differently, their annotations are per se subjective. For this, annotations are typically collected from multiple annotators and averaged to obtai...

p>To train machine learning algorithms to predict emotional expressions in terms of arousal and valence, annotated datasets are needed. However, as different people perceive others’ emotional expressions differently, their annotations are per se subjective. For this, annotations are typically collected from multiple annotators and averaged to obtai...

Algorithmic latency in speech processing is dominated by the frame length used for Fourier analysis, which in turn limits the achievable performance of magnitude-centric approaches. As previous studies suggest the importance of phase grows with decreasing frame length, this work presents a systematic study on the contribution of phase and magnitude...

Phase retrieval is a problem encountered not only in speech and audio processing, but in many other fields such as optics. Iterative algorithms based on non-convex set projections are effective and frequently used for retrieving the phase when only STFT magnitudes are available. While the basic Griffin-Lim algorithm and its variants have been the p...

Recently, diffusion-based generative models have been introduced to the task of speech enhancement. The corruption of clean speech is modeled as a fixed forward process in which increasing amounts of noise are gradually added. By learning to reverse this process in an iterative fashion conditioned on the noisy input, clean speech is generated. We b...

As different people perceive others' emotional expressions differently, their annotation in terms of arousal and valence are per se subjective. To address this, these emotion annotations are typically collected by multiple annotators and averaged across annotators in order to obtain labels for arousal and valence. However, besides the average, also...

Emotions are subjective constructs. Recent end-to-end speech emotion recognition systems are typically agnostic to the subjective nature of emotions, despite their state-of-the-art performance. In this work, we introduce an end-to-end Bayesian neural network architecture to capture the inherent subjectivity in the arousal dimension of emotional exp...

The key advantage of using multiple microphones for speech enhancement is that spatial filtering can be used to complement the tempo-spectral processing. In a traditional setting, linear spatial filtering (beamforming) and single-channel post-filtering are commonly performed separately. In contrast, there is a trend towards employing deep neural ne...

The SepFormer architecture shows very good results in speech separation. Like other learned-encoder models, it uses short frames, as they have been shown to obtain better performance in these cases. This results in a large number of frames at the input, which is problematic; since the SepFormer is transformer-based, its computational complexity dra...

Employing deep neural networks (DNNs) to directly learn filters for multi-channel speech enhancement has potentially two key advantages over a traditional approach combining a linear spatial filter with an independent tempo-spectral post-filter: 1) non-linear spatial filtering allows to overcome potential restrictions originating from a linear proc...

Phase retrieval is a problem encountered not only in speech and audio processing, but in many other fields such as optics. Iterative algorithms based on non-convex set projections are effective and frequently used for retrieving the phase when only STFT magnitudes are available. While the basic Griffin-Lim algorithm and its variants have been the p...

This work focuses on online dereverberation for hearing devices using the weighted prediction error (WPE) algorithm. WPE filtering requires an estimate of the target speech power spectral density (PSD). Recently deep neural networks (DNNs) have been used for this task. However, these approaches optimize the PSD estimate which only indirectly affect...

In this paper, a neural network-augmented algorithm for noise-robust online dereverberation with a Kalman filtering variant of the weighted prediction error (WPE) method is proposed. The filter stochastic variations are predicted by a deep neural network (DNN) trained end-to-end using the filter residual error and signal characteristics. The presen...

A two-stage online dereverberation algorithm for hearing devices is presented in this paper. The approach combines a multi-channel multi-frame linear filtering approach with a single-channel single-frame post-filter. Both components rely on power spectral density (PSD) estimates provided by deep neural networks (DNNs). This contribution extends our...

Score-based generative models (SGMs) have recently shown impressive results for difficult generative tasks such as the unconditional and conditional generation of natural images and audio signals. In this work, we extend these models to the complex short-time Fourier transform (STFT) domain, proposing a novel training task for speech enhancement us...

While phase-aware speech processing has been receiving increasing attention in recent years, most narrowband STFT approaches with frame lengths of about 32ms show a rather modest impact of phase on overall performance. At the same time, modern deep neural network (DNN)-based approaches, like Conv-TasNet, that implicitly modify both magnitude and ph...

Speech enhancement in the time-frequency domain is often performed by estimating a multiplicative mask to extract clean speech. However, most neural network-based methods perform point estimation, i.e., their output consists of a single mask. In this paper, we study the benefits of modeling uncertainty in neural network-based speech enhancement. Fo...

One of the most prominent challenges in the field of diffractive imaging is the phase retrieval (PR) problem: In order to reconstruct an object from its diffraction pattern, the inverse Fourier transform must be computed. This is only possible given the full complex-valued diffraction data, i.e. magnitude and phase. However, in diffractive imaging,...

The key advantage of using multiple microphones for speech enhancement is that spatial filtering can be used to complement the tempo-spectral processing. In a traditional setting, linear spatial filtering (beamforming) and single-channel post-filtering are commonly performed separately. In contrast, there is a trend towards employing deep neural ne...

Recent advances in the design of neural network architectures, in particular those specialized in modeling sequences, have provided significant improvements in speech separation performance. In this work, we propose to use a bio-inspired architecture called Fully Recurrent Convolutional Neural Network (FRCNN) to solve the separation task. This mode...