We introduce MDSGen, a novel framework for vision-guided open-domain sound generation optimized for model parameter size, memory consumption, and inference speed. This framework incorporates two key innovations: (1) a redundant video feature removal module that filters out unnecessary visual information, and (2) a temporal-aware masking strategy that leverages temporal context for enhanced audio generation accuracy. In contrast to existing resource-heavy Unet-based models, \texttt{MDSGen} employs denoising masked diffusion transformers, facilitating efficient generation without reliance on pre-trained diffusion models. Evaluated on the benchmark VGGSound dataset, our smallest model (5M parameters) achieves $97.9$% alignment accuracy, using $172\times$ fewer parameters, $371$% less memory, and offering $36\times$ faster inference than the current 860M-parameter state-of-the-art model ($93.9$% accuracy). The larger model (131M parameters) reaches nearly $99$% accuracy while requiring $6.5\times$ fewer parameters. These results highlight the scalability and effectiveness of our approach. The code is available at https://bit.ly/mdsgen.
MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection
National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China（中国科学技术大学国家语音语言信息处理工程研究中心）；ICT Cluster, Singapore Institute of Technology（新加坡理工学院ICT集群）；The Australian National University（澳大利亚国立大学）
Neural network based architectures used for sound recognition are usually adapted from other application domains, which may not harness sound related properties. The ConditionaL Neural Network (CLNN) is designed to consider the relational properties across frames in a temporal signal, and its extension the Masked ConditionaL Neural Network (MCLNN) embeds a filterbank behavior within the network, which enforces the network to learn in frequency bands rather than bins. Additionally, it automates the exploration of different feature combinations analogous to handcrafting the optimum combination o…
The ConditionaL Neural Network (CLNN) exploits the nature of the temporal sequencing of the sound signal represented in a spectrogram, and its variant the Masked ConditionaL Neural Network (MCLNN) induces the network to learn in frequency bands by embedding a filterbank-like sparseness over the network's links using a binary mask. Additionally, the masking automates the exploration of different feature combinations concurrently analogous to handcrafting the optimum combination of features for a recognition task. We have evaluated the MCLNN performance using the Urbansound8k dataset of environm…
Deep neural network architectures designed for application domains other than sound, especially image recognition, may not optimally harness the time-frequency representation when adapted to the sound recognition problem. In this work, we explore the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural Network (MCLNN) for multi-dimensional temporal signal recognition. The CLNN considers the inter-frame relationship, and the MCLNN enforces a systematic sparseness over the network's links to enable learning in frequency bands rather than bins allowing the network to be frequency s…
Sony CSL Paris（索尼计算机科学实验室巴黎分部）；IRCAM - CNRS UMR 9912 STMS - Sorbonne Université（声学/音乐研究与协作研究所 - 法国国家科学研究中心 UMR 9912 STMS - 索邦大学）
Modern approaches to sound synthesis using deep neural networks are hard to control, especially when fine-grained conditioning information is not available, hindering their adoption by musicians. In this paper, we cast the generation of individual instrumental notes as an inpainting-based task, introducing novel and unique ways to iteratively shape sounds. To this end, we propose a two-step approach: first, we adapt the VQ-VAE-2 image generation architecture to spectrograms in order to convert real-valued spectrograms into compact discrete codemaps, we then implement token-masked Transformers …
Automatic feature extraction using neural networks has accomplished remarkable success for images, but for sound recognition, these models are usually modified to fit the nature of the multi-dimensional temporal representation of the audio signal in spectrograms. This may not efficiently harness the time-frequency representation of the signal. The ConditionaL Neural Network (CLNN) takes into consideration the interrelation between the temporal frames, and the Masked ConditionaL Neural Network (MCLNN) extends upon the CLNN by forcing a systematic sparseness over the network's weights using a bi…
Department of Electronic Engineering University of York（约克大学电子工程系）；University of York（约克大学）
We present the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural Network (MCLNN) designed for temporal signal recognition. The CLNN takes into consideration the temporal nature of the sound signal and the MCLNN extends upon the CLNN through a binary mask to preserve the spatial locality of the features and allows an automated exploration of the features combination analogous to hand-crafting the most relevant features for the recognition task. MCLNN has achieved competitive recognition accuracies on the GTZAN and the ISMIR2004 music datasets that surpass several state-of-the-…
Neural network based architectures used for sound recognition are usually adapted from other application domains such as image recognition, which may not harness the time-frequency representation of a signal. The ConditionaL Neural Networks (CLNN) and its extension the Masked ConditionaL Neural Networks (MCLNN) are designed for multidimensional temporal signal recognition. The CLNN is trained over a window of frames to preserve the inter-frame relation, and the MCLNN enforces a systematic sparseness over the network's links that mimics a filterbank-like behavior. The masking operation induces …
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
The text-based speech editor allows the editing of speech through intuitive cutting, copying, and pasting operations to speed up the process of editing speech. However, the major drawback of current systems is that edited speech often sounds unnatural due to cut-copy-paste operation. In addition, it is not obvious how to synthesize records according to a new word not appearing in the transcript. This paper proposes a novel end-to-end text-based speech editing method called context-aware mask prediction network (CampNet). The model can simulate the text-based speech editing process by randomly …
