Related papers: Apollo: Band-sequence Modeling for High-Quality Au…

Talking head synthesis has emerged as a prominent research topic in computer graphics and multimedia, yet most existing methods often struggle to strike a balance between generation quality and computational efficiency, particularly under…

Audio codecs are typically transform-domain based and efficiently code stationary audio signals, but they struggle with speech and signals containing dense transient events such as applause. Specifically, with these two classes of signals…

Autoregressive (AR) modeling is invaluable in signal processing, in particular in speech and audio fields. Attempts in the literature can be found that regularize or constrain either the time-domain signal values or the AR coefficients,…

This work introduces a feature extracted from stereophonic/binaural audio signals aiming to represent a measure of perceived quality degradation in processed spatial auditory scenes. The feature extraction technique is based on a simplified…

Speech enhancement has seen great improvement in recent years mainly through contributions in denoising, speaker separation, and dereverberation methods that mostly deal with environmental effects on vocal audio. To enhance speech beyond…

Autoregressive music generation depends strongly on the audio tokenizer. Existing high-fidelity codecs often use residual multi-codebook quantization, which preserves reconstruction quality but complicates language modeling after sequence…

Reference Audio-Visual Segmentation (Ref-AVS) tasks challenge models to precisely locate sounding objects by integrating visual, auditory, and textual cues. Existing methods often lack genuine semantic understanding, tending to memorize…

Explainable speech quality assessment requires moving beyond Mean Opinion Scores (MOS) to analyze underlying perceptual dimensions. To address this, we introduce a novel post-training method that tailors the foundational Audio Large…

Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain. In this context,…

Query-based audio source extraction seeks to recover a target source from a mixture conditioned on a query. Existing approaches are largely confined to single-channel audio, leaving the spatial information in multi-channel recordings…

Neural audio autoencoders create compact latent representations that preserve perceptually important information, serving as the foundation for both modern audio compression systems and generation approaches like next-token prediction and…

Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven…

The Fearless Steps APOLLO Community Resource provides unparalleled opportunities to explore the potential of multi-speaker team communications from NASA Apollo missions. This study focuses on discovering the characteristics that make Apollo…

Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, training them to succeed on long-horizon, domain-specialized…

Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we…

There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave…

Audio-based equipment condition monitoring suffers from a lack of standardized methodologies for algorithm selection, hindering reproducible research. This paper addresses this gap by introducing a comprehensive framework for the systematic…

Recent works have shown the capability of deep generative models to tackle general audio synthesis from a single label, producing a variety of impulsive, tonal, and environmental sounds. Such models operate on band-limited signals and, as a…

This paper proposes a novel way of doing audio synthesis at the waveform level using Transformer architectures. We propose a deep neural network for generating waveforms, similar to wavenet. This is fully probabilistic, auto-regressive, and…

In recent years, user-generated audio content has proliferated across various media platforms, creating a growing need for efficient retrieval methods that allow users to search for audio clips using natural language queries. This task,…