相关论文: Impact of Microphone Array Mismatches to Learning-…

Training deep neural networks at the edge on light computational devices, embedded systems and robotic platforms is nowadays very challenging. Continual learning techniques, where complex models are incrementally trained on small batches of…

The acoustic variability of noisy and reverberant speech mixtures is influenced by multiple factors, such as the spectro-temporal characteristics of the target speaker and the interfering noise, the signal-to-noise ratio (SNR) and the room…

Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem. But the performance has been found usually limited due to heavy reliance on environmental…

The paper introduces Diff-Filter, a multichannel speech enhancement approach based on the diffusion probabilistic model, for improving speaker verification performance under noisy and reverberant conditions. It also presents a new two-step…

Telepresence aims to create an immersive but virtual experience of the audio and visual scene at the far end for users at the near end. In this contribution, we propose an array-based binaural rendering system that converts the array…

Audio deepfake detection has become increasingly challenging due to rapid advances in speech synthesis and voice conversion technologies, particularly under channel distortions, replay attacks, and real-world recording conditions. This…

Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…

In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate…

Recently, speech recognition with ad-hoc microphone arrays has received much attention. It is known that channel selection is an important problem of ad-hoc microphone arrays, however, this topic seems far from explored in speech…

Time-division multiplexed (TDM) channel sounders, in which a single RF chain is connected sequentially via an electronic switch to different elements of an array, are widely used for the measurement of double-directional/MIMO propagation…

Blind Speech Separation (BSS) aims to separate multiple speech sources from audio mixtures recorded by a microphone array. The problem is challenging because it is a blind inverse problem, i.e., the microphone array geometry, the room…

The increasing popularity of spatial audio in applications such as teleconferencing, entertainment, and virtual reality has led to the recent developments of binaural reproduction methods. However, only a few of these methods are…

Speaker verification systems have seen significant advancements with the introduction of Multi-scale Feature Aggregation (MFA) architectures, such as MFA-Conformer and ECAPA-TDNN. These models leverage information from various network…

Deep neural networks rely heavily on normalization methods to improve their performance and learning behavior. Although normalization methods spurred the development of increasingly deep and efficient architectures, they also increase the…

Personalized speech enhancement has been a field of active research for suppression of speechlike interferers such as competing speakers or TV dialogues. Compared with single channel approaches, multichannel PSE systems can be more…

Neural networks (NNs) have been widely applied in speech processing tasks, and, in particular, those employing microphone arrays. Nevertheless, most existing NN architectures can only deal with fixed and position-specific microphone arrays.…

Deep Learning has advanced Automatic Speaker Verification (ASV) in the past few years. Although it is known that deep learning-based ASV systems are vulnerable to adversarial examples in digital access, there are few studies on adversarial…

A deep learning model is proposed for reconstructing 2D dielectric breast images from time-domain signals. Unlike existing learning models that employ a fixed antenna array, where input data consists solely of measurements, the proposed…

Large-scale end-to-end models such as Whisper have shown strong performance on diverse speech tasks, but their internal behavior on pathological speech remains poorly understood. Understanding how dysarthric speech is represented across…

The performance of traditional linear spatial filters for speech enhancement is constrained by the physical size and number of channels of microphone arrays. For instance, for large microphone distances and high frequencies, spatial…