@techreport{ChungKT2024,
    Author = "Chung, Hae Chun and Jung, Jae Hoon",
    title = "Sound Scene Synthesis Based on GAN Using Contrastive Learning and Effective Time-Frequency Swap Cross Attention Mechanism",
    institution = "KT Corporation, Seoul, Republic of Korea",
    year = "2024",
    month = "July",
    abstract = "This technical report outlines the efforts of KT Corporation's Acoustic Processing Project for addressing sound scene synthesis, DCASE 2024 Challenge Task 7. The task's objective is to develop a generative system capable of synthesizing environmental sounds from text descriptions. Our system is designed in three stages to achieve this goal: embedding the text description, generating a mel spectrogram conditioned on the text embedding, and converting the mel spectrogram into an audio waveform. Our main focus lies on training the model for the second stage. We employed a generative adversarial network (GAN) and meticulously designed the training process and architecture. We utilized various contrastive losses and introduced the single-double-triple attention mechanism to accurately capture text descriptions and train high-quality features. To mitigate the rise in GPU memory consumption caused by the expanded attention mechanism, we designed a novel time-frequency swap cross-attention mechanism. Our system achieved FAD score more than 30\% lower than the DCASE baseline, demonstrating significant performance improvements in text-to-audio generation."
}

@techreport{LeeGLI2024,
    Author = "Lagrange, Mathieu and Lee, Junwon and Tailleur, Modan and Heller, Laurie and Choi, Keunwoo and McFee, Brian and Imoto, Keisuke and Okamoto, Yuki",
    title = "Correlation of Fréchet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependent",
    institution = "CNRS, Ecole Centrale Nantes, Nantes Universite, Nantes, France and Gaudio Lab, Inc., Seoul, South Korea, KAIST and Daejeon, South Korea and Carnegie Mellon University, Pennsylvania, USA and New York University, New York, USA, and Doshisha University, Kyoto, Japan and Ritsumeikan University, Kyoto, Japan",
    year = "2024",
    month = "July",
    abstract = "",
    journal = "arXiv:2403.17508"
}

@techreport{SunSamsung2024,
    Author = "ZhiDong, Xie and XinYu, Li and HaiCheng, Liu and XiaoYan, Zou and Yu, Sun",
    title = "Sound Scene Synthesis With AudioLDM and TANGO2 for DCASE 2024 Task7",
    institution = "Samsung Research China-Nanjing, Nanjing, China",
    year = "2024",
    month = "July",
    abstract = "This report describes our submission for DCASE2024 Challenge Task 7, a system for sound scene synthesis. Our system is based on AudioLDM and Tango2. Experiments are conducted on the dataset of DCASE2024 Challenge Task 7. The Frechet Audio Distance (FAD) between the sound generated by our system and the develop set is 60.64."
}

@techreport{VermaIITMandi2024,
    Author = "Ghosh, Sagnik and Verma, Gaurav and Shakya, Siddharath Narayan and Sharma, Shubham and Singh, Shivesh",
    title = "Sound Scene Synthesis Based on Fine-Tuned Latent Diffusion Model for DCASE Challenge 2024 Task 7",
    institution = "Indian Institute of Technology Mandi, Kamand, Mandi, India",
    year = "2024",
    month = "July",
    abstract = "With the advancements in generative AI, text-to-audio systems have become increasingly popular, transforming audio generation across various domains such as music and speech. These systems enable the generation of high-quality audio from textual descriptions, offering freedom and control when producing a variety of audio. This technical report explores advancements in deep learning applied to sound generation specifically focusing on environmental sound scene generation. Our approach leverages a Text-toAudio (TTA) system with Contrastive Language-Audio Pretraining (CLAP), Conditional Latent Diffusion Models, a Variational Autoencoder (VAE) decoder, and a HiFi-GAN vocoder where LDM learn continuous audio representations from CLAP embeddings, enhancing synthesis control through natural language prompts. Also finetuned the diffusion model with the custom dataset created using two audio dataset in order to improve generation quality."
}

@techreport{YiSURREY2024,
    Author = "Yuan, Yi and Liu, Haohe and Liu, Xubo and Plumbley, Mark D. and Wang, Wenwu",
    title = "Diffusion Based Sound Scene Synthesis for DCASE Challenge 2024 Task 7",
    institution = "University of Surrey, Guildford, United Kingdom",
    year = "2024",
    month = "July",
    abstract = "Sound scene synthesis aims to generate a variety of environment-related sounds within a specific scene. In this work, we proposed a system for DCASE 2024 challenge task 7. The proposed system is based on the official baseline model AudioLDM, a diffusion-based text-to-audio generation model. The system first trained with large-scale datasets and then downstream into this task via transfer learning. Addressing the challenge of no target audio data, we implemented an automated pipeline to synthesize audio and generate corresponding captions that mirror the semantic structure of the task. Despite the absence of dedicated training and testing sets for this task, our robust audio synthesis model effectively adapts the given conditions, fulfilling all the task requirements. Our system achieved a Fre ́chet Audio Distance (FAD) score of 55.1, surpassing the baseline system's FAD score of 61.3 calculated by the official evaluation toolkit."
}