32 accepted papers
Modern neural networks have greatly improved performance across speech recognition benchmarks. However, gains are often driven by frequent words with limited semantic weight, which can obscure meaningful differences in word error rate, the primary evaluation metric. Errors in rare terms, named entit…
Models initialized from self-supervised pretraining may suffer from poor alignment with downstream tasks, limiting the extent to which subsequent fine-tuning can adapt relevant representations acquired during the pretraining phase. To mitigate this, we introduce BiSSL, a novel bilevel training frame…
Detecting occurrences of keywords with keyword spotting (KWS) systems requires thresholding continuous detection scores. Selecting appropriate thresholds is a non-trivial task, typically relying on optimizing performance on a validation dataset. However, such greedy threshold selection often leads t…
Acoustic feedback cancellation is an important task in audio processing systems, aiming to mitigate the effects of feedback loops on system stability and sound quality. State-of-the-art methods rely on adaptive filtering algorithms and face challenges in balancing between rapid convergence and low s…
Automatic speech recognition (ASR) systems are known to be vulnerable to adversarial attacks. This paper addresses detection and defence against targeted white-box attacks on speech signals for ASR systems. While existing work has utilised diffusion models (DMs) to purify adversarial examples, achie…
We study the Continuous-Discrete Kalman Filter (CD-KF) for State-Space Models (SSMs) where continuous-time dynamics are observed via multiple sensors with discrete, irregularly timed measurements. Our focus extends to scenarios in which the measurement process is coupled with the states of an auxili…
Diffusion models are a new class of generative models that have recently been applied to speech enhancement successfully. Previous works have demonstrated their superior performance in mismatched conditions compared to state-of-the art discriminative models. However, this was investigated with a sin…
In this work, we propose a Multi-Window Masked Autoencoder (MW-MAE) fitted with a novel Multi-Window Multi-Head Attention (MW-MHA) module that facilitates the modelling of local-global interactions in every decoder transformer block through attention heads of several distinct local and global window…
In this paper, we derive a PAC-Bayes bound on the generalisation gap, in a supervised time-series setting for a special class of discrete-time non-linear dynamical systems. This class includes stable recurrent neural networks (RNN), and the motivation for this work was its application to RNNs. In or…
In this paper we derive a PAC-Bayesian error bound for a class of stochastic dynamical systems with inputs, namely, for linear time-invariant stochastic state-space models (stochastic LTI systems for short). This class of systems is widely used in control engineering and econometrics, in particular,…
In this paper, we propose the use of self-supervised pretraining on a large unlabelled data set to improve the performance of a personalized voice activity detection (VAD) model in adverse conditions. We pretrain a long short-term memory (LSTM)-encoder using the autoregressive predictive coding (APC…
In the context of keyword spotting (KWS), the replacement of handcrafted speech features by learnable features has not yielded superior KWS performance. In this study, we demonstrate that filterbank learning outperforms handcrafted speech features for KWS whenever the number of filterbank channels i…
This paper leverages the potential of Large Intelligent Surfaces (LIS) for radio sensing in 6G wireless networks. By taking advantage of arbitrary communication signals occurring in the scenario, we apply direct processing to the output signal from the LIS to obtain a radio map that describes the ph…
This paper considers speech enhancement of signals picked up in one noisy environment which must be presented to a listener in another noisy environment. Recently, it has been shown that an optimal solution to this problem requires the consideration of the noise sources in both environments jointly.…
The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic spe…
In this paper, we present a deep-learning-based framework for audio-visual speech inpainting, i.e., the task of restoring the missing parts of an acoustic speech signal from reliable audio context and uncorrupted visual information. Recent work focuses solely on audio-only methods and generally aims…
Acoustic beamforming is crucial for many applications where ex-traction of a target signal from a noisy environment is required. In order to implement practical beamformers, e.g. the multichannel Wiener filter (MWF), estimation of the target and noise power spectral densities (PSDs), and the relativ…
Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning algorithm. To defend the learning systems from these attacks, ex…
In headset and hearing aid applications, it is of interest to retrieve the user's own voice in a noisy environment, e.g. for telephony applications. To do so, the cross-power spectral density (CPSD) of the interference-plus-noise is required. In this paper, a novel maximum likelihood (ML) estimator…
Humans tend to change their way of speaking when they are immersed in a noisy environment, a reflex known as Lombard effect. Current speech enhancement systems based on deep learning do not usually take into account this change in the speaking style, because they are trained with neutral (non-Lombar…
Audio-visual speech enhancement (AV-SE) is the task of improving speech quality and intelligibility in a noisy environment using audio and visual information from a talker. Recently, deep learning techniques have been adopted to solve the AV-SE task in a supervised manner. In this context, the choic…
In this paper we propose a Deep Neural Network (D NN) based Speech Enhancement (SE) system that is designed to maximize an approximation of the Short-Time Objective Intelligibility (STOI) measure. We formalize an approximate-STOI cost function and derive analytical expressions for the gradients requ…
The public perception of android robots is a field of growing applied relevance. Currently, most androids are confined within controlled environments rendering interactions between potential end-users, and robots challenging. Even more challenging is for researchers to investigate end-users' percept…
We propose a non-intrusive intelligibility measure for noisy and non-linearly processed speech, i.e. a measure which can predict intelligibility from a degraded speech signal without requiring a clean reference signal. The proposed measure is based on the Short-Time Objective Intelligibility (STOI)…
We propose a novel deep learning training criterion, named permutation invariant training (PIT), for speaker independent multi-talker speech separation, commonly known as the cocktail-party problem. Different from the multi-class regression technique and the deep clustering (DPCL) technique, our nov…
This paper describes a new database for the assessment of automatic speaker verification (ASV) vulnerabilities to spoofing attacks. In contrast to other recent data collection efforts, the new database has been designed to support the development of replay spoofing countermeasures tailored towards t…
We propose and evaluate a binaural speech intelligibility measure. The measure is a binaural extension of the Short-Time Objective Intelligibility (STOI) measure and focuses on predicting the intelligibility of noisy speech which has been enhanced by a speech processing algorithm (e.g. in a hearing…
In this paper, we propose a Direction of Arrival (DoA) estimator for a Hearing Aid System (HAS) which can connect to a wireless microphone worn by a target talker. The wireless microphone "informs" the HAS about the almost noise-free content of the target sound, and the proposed DoA estimator uses t…
The use of social robots for elderly care is becoming ever more relevant, thus introducing new challenges which need to be solved to achieve acceptable performance. One fundamental task for a social robot is to move to the person of interest in order to start interacting or perform a service. In thi…
Most state-of-the-art Sound Source Localization (SSL) algorithms have been proposed for applications which are “uninformed” about the target sound content; however, utilizing a wireless microphone worn by a target talker, enables recent Hearing Aid Systems (HASs) to access to an almost noise-free so…
The direction dependence of Head Related Transfer Functions (HRTFs) forms the basis for HRTF-based Sound Source Localization (SSL) algorithms. In this paper, we show how spectral similarities of the HRTFs of different directions in the horizontal plane influence performance of HRTF-based SSL algorit…
An i-vector is a low-dimensional fixed-length representation of a variable-length speech utterance, and is defined as the posterior mean of a latent variable conditioned on the observed feature sequence of an utterance. The assumption is that the prior for the latent variable is non-informative, sin…