Related papers: Pre-training Autoencoder for Acoustic Event Classi…

Sound event detection is the task of recognizing sounds and determining their extent (onset/offset times) within an audio clip. Existing systems commonly predict sound presence confidence in short time frames. Then, thresholding produces…

Acoustic Scene Classification (ASC) and Sound Event Detection (SED) are two separate tasks in the field of computational sound scene analysis. In this work, we present a new dataset with both sound scene and sound event labels and use this…

Acoustic echo cancellation (AEC) is an important speech signal processing technology that can remove echoes from microphone signals to enable natural-sounding full-duplex speech communication. While single-channel AEC is widely adopted,…

We propose a novel approach to end-to-end automatic speech recognition (ASR) to achieve efficient speech in-context learning (SICL) for (i) long-form speech decoding, (ii) test-time speaker adaptation, and (iii) test-time contextual…

Acoustic Echo Cancellation (AEC) plays a key role in speech interaction by suppressing the echo received at microphone introduced by acoustic reverberations from loudspeakers. Since the performance of linear adaptive filter (AF) would…

Brain computer interface applications can be used to overcome learning problems, especially student anxiety, lack of focus, and lack of attention. This paper introduces a system based on brain computer interface (BCI) to be used in…

Sparse autoencoders (SAEs) have emerged as a promising approach for learning interpretable features from neural network activations. However, the optimization landscape for SAE training can be challenging due to correlations in the input…

We present a model of the self-calibration of active binocular vision comprising the simultaneous learning of visual representations, vergence, and pursuit eye movements. The model follows the principle of Active Efficient Coding (AEC), a…

Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module,…

With the ever-increasing electrification of the vehicle showing no sign of retreating, electronic systems deployed in automotive applications are subject to more stringent Electromagnetic Immunity compliance constraints than ever before, to…

The combined electric and acoustic stimulation (EAS) has demonstrated better speech recognition than conventional cochlear implant (CI) and yielded satisfactory performance under quiet conditions. However, when noise signals are involved,…

Advancements in optical quantum technologies have been enabled by the generation, manipulation, and characterization of light, with identification based on its photon statistics. However, characterizing light and its sources through single…

Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promising to be large-scale adopted. For the sake of practicality, a thorough…

In this report, we propose three novel methods for developing a sound event detection (SED) model for the DCASE 2024 Challenge Task 4. First, we propose an auxiliary decoder attached to the final convolutional block to improve feature…

In this paper, we evaluate deep learning-enabled AED systems against evasion attacks based on adversarial examples. We test the robustness of multiple security critical AED tasks, implemented as CNNs classifiers, as well as existing…

A method for musical audio synthesis using autoencoding neural networks is proposed. The autoencoder is trained to compress and reconstruct magnitude short-time Fourier transform frames. The autoencoder produces a spectrogram by activating…

We introduce CAN, a simple, efficient and scalable method for self-supervised learning of visual representations. Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the…

Bioacoustic sound event detection allows for better understanding of animal behavior and for better monitoring biodiversity using audio. Deep learning systems can help achieve this goal, however it is difficult to acquire sufficient…

Audio classification and restoration are among major downstream tasks in audio signal processing. However, restoration derives less of a benefit from pretrained models compared to the overwhelming success of pretrained models in…

Event camera has significant advantages in capturing dynamic scene information while being prone to noise interference, particularly in challenging conditions like low threshold and low illumination. However, most existing research focuses…