arXiv:2608. 11627v1 Announce Type: cross Abstract: The Relative Transfer Matrix (ReTM), recently introduced as a generalization of the relative transfer function for multiple receivers and sources, shows promising performance when applied to speech enhancement in noisy environments.
arXiv:2607. 04471v1 Announce Type: cross Abstract: Linear spatial filters (beamformers) enable robust, generalizable and interpretable speech enhancement with performance guarantees under ideal parameterization.
arXiv:2606. 18664v1 Announce Type: cross Abstract: Reliable sound source localization is fundamental to robot audition, enabling autonomous robots to perceive spatial cues and operate effectively in dynamic environments.
arXiv:2606. 09677v1 Announce Type: cross Abstract: While discriminative models for multi-channel speech separation excel in reference-based metrics, they often exhibit suboptimal human listening quality.
arXiv:2607. 01295v1 Announce Type: cross Abstract: Acoustic imaging visualization is a core methodology in acoustics, enabling spatial analysis of sound sources and acoustic scenes.
arXiv:2608. 15690v1 Announce Type: cross Abstract: Text-to-audio-video (T2AV) generation models produce a video and its soundtrack from a textual description, but offer no control over whose voice speaks in the output.
Reliable sound source localization is fundamental to robot audition, enabling autonomous robots to perceive spatial cues and operate effectively in dynamic environments. Classical methods such as Multiple Signal Classification (MUSIC) offer strong theoretical foundations but degrade under low signal-to-noise ratios.
arXiv:2604. 24199v4 Announce Type: replace-cross Abstract: We propose Speech Enhancement based on Drifting Models (DriftSE), a novel generative framework that formulates denoising as an equilibrium problem.
arXiv:2606. 31552v1 Announce Type: cross Abstract: Room-acoustic simulations are widely used to augment training data for deep-learning-based speech enhancement.
arXiv:2602. 20967v2 Announce Type: replace-cross Abstract: Automatic speech recognition (ASR) degrades severely in noisy environments.
arXiv:2607. 00363v1 Announce Type: cross Abstract: Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage.
arXiv:2606. 16532v1 Announce Type: cross Abstract: Audio deepfake detectors often fail to generalize across speakers, as they learn speaker-identity features rather than synthesis artifacts, known as implicit identity leakage.
arXiv:2510. 20441v2 Announce Type: replace-cross Abstract: Neural audio codecs have largely promoted the application of language models (LMs) for speech applications.