CORTEXA
← Browse
arxiveess.AScs.AI2026-07-14

Efficient Text-to-Audio Generation via Pruning

Arshdeep Singh, Yi Yuan, Yun Chen, Wenwu Wang, Mark D. Plumbley

Diffusion-based text-to-audio generative models such as AudioLDM achieve high perceptual quality and strong semantic consistency; however, their practical deployment is hindered by the substantial computational cost of the U-Net denoising backbone. In this work, we apply model pruning to improve the computational efficiency of AudioLDM, a U-Net-based text-conditioned audio latent diffusion model. We analyse parameter redundancy across U-Net convolutional blocks and evaluate a filter-pruning strategy. Pruning is guided by norm-based criteria and followed by lightweight finetuning to recover performance losses. Experimental results demonstrate that up to 83% of the parameters and 39% of the multiply-accumulate operations of U-Net have been reduced while maintaining, and in some cases improving, generation quality compared to the baseline unpruned network. We find that pruning affects AudioLDM's ability to generate certain sound events including safety-critical sounds such as gunshots, sirens, and explosions, as well as mechanical sounds such as drills and sewing machines, and other sounds such as sprays and tick-tocks, which are mostly recovered by lightweight finetuning of the pruned model.

View free PDFSource page

Related papers

arxivcs.SDcs.AIcs.MMeess.AS2026-06-30

SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation

Binh Mai, Tran Quoc Bao Le, Hung Dinh, Cong Tran

Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step denoising. Existing one-step approaches alleviate this issue but still rely on paired text--audio data during distillation. To addres…

View free PDFSource page
arxiveess.AScs.AIcs.CLcs.LGcs.SD2026-07-15

Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models

Chun-Yi Kuan, Siwon Kim, Byeonggeun Kim, Suyoun Kim, Bo-Ru Lu, Qinming Tang, et al.

Recent text-to-audio models generate high-quality audio, but often fail to follow instructions involving multiple sound events and temporal order. This gap arises because existing evaluation and training signals mainly emphasize global similarity or perceptual quality, with limit…

View free PDFSource page
arxivcs.CLcs.AIcs.LGcs.SDeess.AS2026-07-06

Unified Audio Intelligence Without Regressing on Text Intelligence

Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim, Boxin Wang, Zihan Liu, Sungwon Kim, et al.

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. Audex adopts a simple unifie…

View free PDFSource page
arxiveess.AScs.AI2026-07-02

An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation

Haoran Wang, Jinchuan Tian, Siddhant Arora, Shinji Watanabe

While Large Multimodal Models excel in comprehension, high-throughput inference engines lack native support for multimodal generation. This is severe in Speech Language Models, where generating multi-layered audio tokens via decoupled AR+NAR or synchronous Multi-Token Prediction…

View free PDFSource page
arxivcs.SDcs.AIeess.ASeess.SPeess.SY2026-07-10

A Production-Oriented Framework for Evaluation of SFX Generation

Mélodie Desbos, Yara Bahram, Eric Granger, Mohammadhadi Shateri

Industrial sound design requires audio generation systems that not only produce realistic audio, but also preserve the perceptual identity of a reference, support controllable variation, and remain efficient for practical workflows. Existing evaluations are usually tied to text-t…

View free PDFSource page
arxivcs.SDcs.AIeess.ASeess.SP2026-07-10

ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models

Sang-Hoon Lee, Ha-Yeong Choi

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. To address this issue, we propose R…

View free PDFSource page