Related papers: The CARFAC v2 Cochlear Model in Matlab, NumPy, and…

Dysarthric speech recognition has posed major challenges due to lack of training data and heavy mismatch in speaker characteristics. Recent ASR systems have benefited from readily available pretrained models such as wav2vec2 to improve the…

We consider the problem of precision matrix estimation where, due to extraneous confounding of the underlying precision matrix, the data are independent but not identically distributed. While such confounding occurs in many scientific…

This paper proposes a flexible multichannel speech enhancement system with the main goal of improving robustness of automatic speech recognition (ASR) in noisy conditions. The proposed system combines a flexible neural mask estimator…

This paper proposes a novel framework for audio deepfake detection with two main objectives: i) attaining the highest possible accuracy on available fake data, and ii) effectively performing continuous learning on new fake data in a…

An active dissipative process organizes auditory frequency analysis in the mammalian cochlea. A minimal active beam model reveals that a spatially varying viscous coupling operator, $\partial_{xx}\kappa\partial_{xx}$, generates dissipative…

Few-shot learning (FSL) often requires effective adaptation of models using limited labeled data. However, most existing FSL methods rely on entangled representations, requiring the model to implicitly recover the unmixing process to obtain…

Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining…

Photoacoustic imaging (PAI) is a promising medical imaging modality providing the spatial resolution of ultrasound (US) imaging and the contrast of pure optical imaging. For linear-array PAI, a beamformer has to be used as the…

Acoustic echo cancellation (AEC) in full-duplex communication systems eliminates acoustic feedback. However, nonlinear distortions induced by audio devices, background noise, reverberation, and double-talk reduce the efficiency of…

Deriving multimodal representations of audio and lexical inputs is a central problem in Natural Language Understanding (NLU). In this paper, we present Contrastive Aligned Audio-Language Multirate and Multimodal Representations (CALM), an…

Contrastive Language-Audio Pretraining (CLAP) is pre-trained to associate audio features with human language, making it a natural zero-shot classifier to recognize unseen sound categories. To adapt CLAP to downstream tasks, prior works…

Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research. With the development of pretraining methods on audio and text data, it is imperative to transfer the knowledge from…

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…

Large Language Models (LLMs) typically rely on a large number of parameters for token embedding, leading to substantial storage requirements and memory footprints. In particular, LLMs deployed on edge devices are memory-bound, and reducing…

Australia Telescope Compact Array (ATCA) observations in sky regions selected to be low in foreground confusion have been used to infer limits on arcmin-scale CMB anisotropy in total intensity and polarization. These deep searches have,…

Since its inception, the ReSpect program has been evolving to provide powerful tools for simulating spectroscopic processes and exploring emerging research areas, all while incorporating relativistic effects, particularly spin-orbit…

Medical datasets and especially biobanks, often contain extensive tabular data with rich clinical information in addition to images. In practice, clinicians typically have less data, both in terms of diversity and scale, but still wish to…

Transformers face scalability challenges due to the quadratic cost of attention, which involves dense similarity computations between queries and keys. We propose CAMformer, a novel accelerator that reinterprets attention as an associative…

Audio impairment recognition is based on finding noise in audio files and categorising the impairment type. Recently, significant performance improvement has been obtained thanks to the usage of advanced deep learning models. However,…

This paper reports on the design and outcomes of the ICASSP SP Clarity Challenge: Speech Enhancement for Hearing Aids. The scenario was a listener attending to a target speaker in a noisy, domestic environment. There were multiple…