arXiv:2607. 12417v1 Announce Type: new Abstract: Although vast amounts of data, such as audio signal spectra, are naturally represented using complex numbers, conventional machine learning methods often simplify complex-domain problems by employing frameworks designed for real-valued variables.
arXiv:2509. 04899v4 Announce Type: replace-cross Abstract: Restricted Boltzmann machines (RBMs) are energy-based models originating from statistical physics, in which hidden units mediate the probability distribution of high-dimensional visible configurations.
arXiv:2608.29763v1 Announce Type: new Abstract: Broad Learning System (BLS) is an efficient alternative to deep architectures due to its fast training, analytical learning, and strong generalization...
MADS (Multi-view Acoustic Descriptor Set) is a compact 19‑dimensional, physics‑informed descriptor set designed to capture spectral, temporal, mechanical, and stochastic aspects of audio signals. Unlike traditional log‑mel or MFCC representations, MADS encodes excitation, damping, periodicity, impulsiveness, and structural consistency in a unified multi‑view format. Evaluated on ESC‑10, ESC‑50, and MSoS datasets with classical machine learning models, MADS outperforms conventional 26‑D MFCC and 38‑D spectral‑summary baselines, achieving 81.00% on ESC‑10, 52.78% on ESC‑50, and 67.48% on MSoS while using roughly half the dimensionality of the 38‑D baseline.
arXiv:2606. 24087v1 Announce Type: new Abstract: Reconstructing continuous speech from scalp electroencephalography (EEG) remains fundamentally challenging.
Dominant audio classification pipelines rely either on compact handcrafted summaries or on fixed time-frequency frontends such as log-mel representations prior to deep modeling. While highly successfu...
The paper introduces Langevin simulated bifurcation (LSB), a fast, parallel Boltzmann sampler that matches the accuracy of sequential MCMC methods. It also proposes conditional expectation matching (CEM), an efficient technique for estimating the effective temperature of samples from energy‑based models with conditional independence. Building on these, the authors develop sampler adaptive learning (SAL), which adjusts the model temperature to align with the distribution produced by LSB, enabling efficient training of semi‑restricted Boltzmann machines (SRBMs) and outperforming conventional methods on synthetic spin‑glass datasets.
FireRedAudio is a 9‑billion‑parameter audio language model that separates continuous input representations for audio understanding and speech generation, enabling a single autoregressive LLM to perform tasks such as ASR, zero‑shot TTS, Instruct TTS, and semantic/acoustic speech editing. The model uses a dedicated Audio Encoder for recognition and a RedAE‑based pathway for generation, with the LLM directly generating text or conditioning a flow‑matching DiT to produce acoustic latents. Evaluations show competitive or leading performance in multilingual ASR, content‑accurate zero‑shot TTS, strong instruction following, and significant improvements in speech editing over prior work.
arXiv:2412. 11449v2 Announce Type: replace-cross Abstract: We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture.
arXiv:2505. 11635v2 Announce Type: cross Abstract: Many real-world tasks, from associative memory to symbolic reasoning, benefit from discrete, structured representations that standard continuous latent models can struggle to express.
arXiv:2607. 11801v1 Announce Type: cross Abstract: Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content.
arXiv:2606. 04103v1 Announce Type: cross Abstract: Conventional hearing aids rely on fixed, frequency-dependent amplification and compression to manage reduced sensitivity, which often fails to provide sufficient listening support in complex environments, such as situations with multiple speakers (the ``cocktail party'' problem).
arXiv:2607. 03806v1 Announce Type: cross Abstract: Audio foundation models are widely adopted as general-purpose feature extractors, yet the internal structure of their learned representations remains insufficiently understood.