Conditional Flow Matching models for text‑to‑speech often produce incoherent frequency evolution during inference. The authors propose a training‑free, frequency‑selective boosting strategy that uses the Discrete Wavelet Transform to dynamically modulate mel‑spectrogram sub‑bands during ODE integration, penalizing aggressive low‑frequency growth while boosting lagging high‑frequency details. Across multiple architectures, this method reduces the number of function evaluations from 32 to 26 and improves Frechet Audio Distance by up to 61% without harming mean opinion scores, speaker similarity, or intelligibility.
arXiv:2607. 09134v1 Announce Type: cross Abstract: Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity.
arXiv:2609.24138v1 Announce Type: cross Abstract: Generative models have recently demonstrated considerable promise in speech super-resolution (SSR). Nevertheless, the majority of existing work has c...
arXiv:2609.38887v1 Announce Type: cross Abstract: Real-time voice conversion (VC) systems commonly rely on pretrained speaker embeddings from automatic speaker verification (ASV) models. While effect...
Generative models have recently demonstrated considerable promise in speech super-resolution (SSR). Nevertheless, the majority of existing work has concentrated on standard or versatile SSR configurat...
arXiv:2605. 22083v2 Announce Type: replace-cross Abstract: While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment.
arXiv:2606. 09048v1 Announce Type: cross Abstract: Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling.
arXiv:2601. 09239v5 Announce Type: replace-cross Abstract: Speech tokenizers are a key building block of fully discrete Speech LLMs.
Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM.
arXiv:2606. 02631v1 Announce Type: cross Abstract: This paper studies whether audio, images, and video can share a common wavelet token schema rather than relying on separate modality-specific latent grids.
arXiv:2606. 09234v1 Announce Type: cross Abstract: Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive large language model (LLM), and a diffusion based flow-matching (FM) model, with these components trained independently.
arXiv:2607. 05196v1 Announce Type: cross Abstract: Audio intelligence involves understanding, reasoning about, and generating both audio and speech.
arXiv:2606. 07080v1 Announce Type: cross Abstract: We present dots.