Related papers: EfficientLEAF: A Faster LEarnable Audio Frontend o…

Adaptive filters (AFs) are vital for enhancing the performance of downstream tasks, such as speech recognition, sound event detection, and keyword spotting. However, traditional AF design prioritizes isolated signal-level objectives, often…

Adaptive Local Iterative Filtering (ALIF) is a currently proposed novel time-frequency analysis tool. It has been empirically shown that ALIF is able to separate components and overcome the mode-mixing problem. However, so far its…

Acoustic echo cancellation (AEC) remains challenging in real-world environments due to nonlinear distortions caused by low-cost loudspeakers and complex room acoustics. To mitigate these issues, we introduce a dual-microphone configuration,…

Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet remains challenging due to two key factors: (1) label scarcity stemming from the high cost of annotations and (2) homophily disparity at node and class…

In recent years, speaker recognition systems based on raw waveform inputs have received increasing attention. However, the performance of such systems are typically inferior to the state-of-the-art handcrafted feature-based counterparts,…

We present FLAMO, a Frequency-sampling Library for Audio-Module Optimization designed to implement and optimize differentiable linear time-invariant audio systems. The library is open-source and built on the frequency-sampling filter design…

Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to mel-spectrogram acoustic features, which are convenient for…

In neural network models, soft mixtures of fixed candidate components (e.g., logic gates and sub-networks) are often used during training for stable optimization, while hard selection is typically used at inference. This raises questions…

Federated learning (FL) is an effective paradigm for enhancing the learning capability of edge devices while preserving data privacy. In geographically dispersed FL systems, such as sensor networks in remote areas, unmanned aerial vehicles…

Many audio applications rely on filter banks (FBs) to analyze, process, and re-synthesize sounds. To approximate the auditory frequency resolution in the signal chain, some applications rely on perceptually motivated FBs, the gammatone FB…

Neural audio codecs are widely used as tokenizers for spoken language models, but they are optimized for waveform reconstruction rather than autoregressive prediction. This mismatch injects acoustically driven uncertainty into the discrete…

In this work, we investigate if the learned encoder of the end-to-end convolutional time domain audio separation network (Conv-TasNet) is the key to its recent success, or if the encoder can just as well be replaced by a deterministic…

We propose a novel pitch estimation technique called DeepF0, which leverages the available annotated data to directly learns from the raw audio in a data-driven manner. F0 estimation is important in various speech processing and music…

Wi-Fi systems based on the IEEE 802.11 standards are the most popular wireless interfaces that use Listen Before Talk (LBT) method for channel access. The distinctive feature of a majority of LBT-based systems is that the transmitters use…

Solving tasks such as speaker recognition, music classification, or semantic audio event tagging with deep learning models typically requires computationally demanding networks. General-purpose audio embeddings (GPAEs) are dense…

Federated learning (FL) offers privacy-preserving decentralized machine learning, optimizing models at edge clients without sharing private data. Simultaneously, foundation models (FMs) have gained traction in the artificial intelligence…

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio…

Source separation and other audio applications have traditionally relied on the use of short-time Fourier transforms as a front-end frequency domain representation step. The unavailability of a neural network equivalent to forward and…

Multi-modal contrastive learning techniques in the audio-text domain have quickly become a highly active area of research. Most works are evaluated with standard audio retrieval and classification benchmarks assuming that (i) these models…

This paper describes a submission to the Environment-Aware Speech and Sound Deepfake Detection Challenge (ESDD2) 2026, which addresses component-level deepfake detection using the CompSpoofV2 dataset, where speech and environmental sounds…