Efficient Text-to-Audio Generation via Pruning

• URL: http://arxiv.org/abs/2607.13330v1
• Date: Tue, 14 Jul 2026 23:22:27 GMT
• Title: Efficient Text-to-Audio Generation via Pruning
• Abstract summary: Pruning is guided by norm-based criteria and followed by lightweight finetuning to recover performance losses.<n>We find that pruning affects AudioLDM's ability to generate certain sound events including safety-critical sounds such as gunshots, sirens, and explosions.
• Score: 25.43908075335463
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting [59.868414584142336]
  DropoutTS is a model-agnostic plugin that shifts the paradigm from "what" to "how much" to learn.<n>It maps noise to adaptive dropout rates - selectively suppressing spurious fluctuations while preserving fine-grained fidelity.
  arXiv  Detail & Related papers  (2026-01-29T13:49:20Z)
• Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine [16.046905753937384]
  This work introduces an efficient ACoM method that can compress and quantize any chosen intermediate feature representation of an already trained speech/audio downstream model.<n>Our approach employs task-specific loss guidance alongside residual vector quantization (RVQ) losses, providing ultra-low codecs (i.e., less than 200 bps) with a minimal loss of the downstream model performance.
  arXiv  Detail & Related papers  (2025-07-17T00:32:07Z)
• Do we really have to filter out random noise in pre-training data for language models? [38.30911856420568]
  Pre-training text data curated from the Internet inevitably contains random noise caused by decoding errors or unregulated web content.<n>We show that the resulting increase in the loss of next-token prediction (NTP) was significantly lower than the proportion of random noise even when the model was scaled up to 2.7B.<n>We introduce a novel plug-and-play Local Gradient Matching loss, which explicitly enhances the denoising capability of the downstream task head by aligning the gradient of normal and perturbed features without requiring knowledge of the model's parameters.
  arXiv  Detail & Related papers  (2025-02-10T16:01:55Z)
• A Real-Time Voice Activity Detection Based On Lightweight Neural [4.589472292598182]
  Voice activity detection (VAD) is the task of detecting speech in an audio stream. Recent neural network-based VADs have alleviated the degradation of performance to some extent. We propose a lightweight and real-time neural network called MagicNet, which utilizes casual and depth separable 1-D convolutions and GRU.
  arXiv  Detail & Related papers  (2024-05-27T03:31:16Z)
• CheapNET: Improving Light-weight speech enhancement network by projected loss function [0.8192907805418583]
  We introduce a novel projection loss function, diverging from MSE, to enhance noise suppression. For echo cancellation, the function enables direct predictions on LAEC pre-processed outputs. Our noise suppression model achieves near state-of-the-art results with only 3.1M parameters and 0.4GFlops/s computational load.
  arXiv  Detail & Related papers  (2023-11-27T16:03:42Z)
• Improving the Robustness of Summarization Models by Detecting and Removing Input Noise [50.27105057899601]
  We present a large empirical study quantifying the sometimes severe loss in performance from different types of input noise for a range of datasets and model sizes. We propose a light-weight method for detecting and removing such noise in the input during model inference without requiring any training, auxiliary models, or even prior knowledge of the type of noise.
  arXiv  Detail & Related papers  (2022-12-20T00:33:11Z)
• Simple Pooling Front-ends For Efficient Audio Classification [56.59107110017436]
  We show that eliminating the temporal redundancy in the input audio features could be an effective approach for efficient audio classification. We propose a family of simple pooling front-ends (SimPFs) which use simple non-parametric pooling operations to reduce the redundant information. SimPFs can achieve a reduction in more than half of the number of floating point operations for off-the-shelf audio neural networks.
  arXiv  Detail & Related papers  (2022-10-03T14:00:41Z)
• A Study of Designing Compact Audio-Visual Wake Word Spotting System Based on Iterative Fine-Tuning in Neural Network Pruning [57.28467469709369]
  We investigate on designing a compact audio-visual wake word spotting (WWS) system by utilizing visual information. We introduce a neural network pruning strategy via the lottery ticket hypothesis in an iterative fine-tuning manner (LTH-IF) The proposed audio-visual system achieves significant performance improvements over the single-modality (audio-only or video-only) system under different noisy conditions.
  arXiv  Detail & Related papers  (2022-02-17T08:26:25Z)
• Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction [109.44933866397123]
  Noise robustness is essential for deploying automatic speech recognition systems in real-world environments. We employ a noise-robust representation learned by a refined self-supervised framework for noisy speech recognition. We achieve comparable performance to the best supervised approach reported with only 16% of labeled data.
  arXiv  Detail & Related papers  (2021-10-28T20:39:02Z)
• Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding [76.89426311082927]
  Existing models are trained on clean data, which causes a textitgap between clean data training and real-world inference. We propose a method from the perspective of domain adaptation, by which both high- and low-quality samples are embedding into similar vector space. Experiments on the widely-used dataset, Snips, and large scale in-house dataset (10 million training examples) demonstrate that this method not only outperforms the baseline models on real-world (noisy) corpus but also enhances the robustness, that is, it produces high-quality results under a noisy environment.
  arXiv  Detail & Related papers  (2021-04-13T17:54:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.