Taming Data and Transformers for Audio Generation

• URL: http://arxiv.org/abs/2406.19388v2
• Date: Thu, 24 Oct 2024 17:56:21 GMT
• Title: Taming Data and Transformers for Audio Generation
• Authors: Moayed Haji-Ali, Willi Menapace, Aliaksandr Siarohin, Guha Balakrishnan, Sergey Tulyakov, Vicente Ordonez,
• Abstract summary: AutoCap is a high-quality and efficient automatic audio captioning model. GenAu is a scalable transformer-based audio generation architecture. We compile 57M ambient audio clips, forming AutoReCap-XL, the largest available audio-text dataset.
• Score: 49.54707963286065
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating ambient sounds is a challenging task due to data scarcity and often insufficient caption quality, making it difficult to employ large-scale generative models for the task. In this work, we tackle this problem by introducing two new models. First, we propose AutoCap, a high-quality and efficient automatic audio captioning model. By using a compact audio representation and leveraging audio metadata, AutoCap substantially enhances caption quality, reaching a CIDEr score of 83.2, marking a 3.2% improvement from the best available captioning model at four times faster inference speed. Second, we propose GenAu, a scalable transformer-based audio generation architecture that we scale up to 1.25B parameters. Using AutoCap to generate caption clips from existing audio datasets, we demonstrate the benefits of data scaling with synthetic captions as well as model size scaling. When compared to state-of-the-art audio generators trained at similar size and data scale, GenAu obtains significant improvements of 4.7% in FAD score, 22.7% in IS, and 13.5% in CLAP score, indicating significantly improved quality of generated audio compared to previous works. Moreover, we propose an efficient and scalable pipeline for collecting audio datasets, enabling us to compile 57M ambient audio clips, forming AutoReCap-XL, the largest available audio-text dataset, at 90 times the scale of existing ones. Our code, model checkpoints, and dataset are publicly available.

Related papers

• Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data [69.7174072745851]
  We present Synthio, a novel approach for augmenting small-scale audio classification datasets with synthetic data. To overcome the first challenge, we align the generations of the T2A model with the small-scale dataset using preference optimization. To address the second challenge, we propose a novel caption generation technique that leverages the reasoning capabilities of Large Language Models.
  arXiv  Detail & Related papers  (2024-10-02T22:05:36Z)
• Improving Text-To-Audio Models with Synthetic Captions [51.19111942748637]
  We propose an audio captioning pipeline that uses an textitaudio language model to synthesize accurate and diverse captions for audio at scale. We leverage this pipeline to produce a dataset of synthetic captions for AudioSet, named textttAF-AudioSet, and then evaluate the benefit of pre-training text-to-audio models on these synthetic captions.
  arXiv  Detail & Related papers  (2024-06-18T00:02:15Z)
• Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning [50.28566759231076]
  We propose an innovative, automatic approach to establish an audio dataset with high-quality captions. Specifically, we construct a large-scale, high-quality, audio-language dataset, named as Auto-ACD, comprising over 1.5M audio-text pairs. We employ LLM to paraphrase a congruent caption for each audio, guided by the extracted multi-modality clues.
  arXiv  Detail & Related papers  (2023-09-20T17:59:32Z)
• Retrieval-Augmented Text-to-Audio Generation [36.328134891428085]
  We show that the state-of-the-art models, such as AudioLDM, are biased in their generation performance. We propose a simple retrieval-augmented approach for TTA models. We show that Re-AudioLDM can generate realistic audio for complex scenes, rare audio classes, and even unseen audio types.
  arXiv  Detail & Related papers  (2023-09-14T22:35:39Z)
• WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research [82.42802570171096]
  We introduce WavCaps, the first large-scale weakly-labelled audio captioning dataset, comprising approximately 400k audio clips with paired captions. Online-harvested raw descriptions are highly noisy and unsuitable for direct use in tasks such as automated audio captioning. We propose a three-stage processing pipeline for filtering noisy data and generating high-quality captions, where ChatGPT, a large language model, is leveraged to filter and transform raw descriptions automatically.
  arXiv  Detail & Related papers  (2023-03-30T14:07:47Z)
• Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models [65.18102159618631]
  multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio pairs, and the complexity of modeling long continuous audio data. We propose Make-An-Audio with a prompt-enhanced diffusion model that addresses these gaps.
  arXiv  Detail & Related papers  (2023-01-30T04:44:34Z)
• AudioGen: Textually Guided Audio Generation [116.57006301417306]
  We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive model that generates audio samples conditioned on text inputs.
  arXiv  Detail & Related papers  (2022-09-30T10:17:05Z)
• HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection [43.50970305209596]
  HTS-AT is an audio transformer with a hierarchical structure to reduce the model size and training time. It achieves better performance in event localization than the previous CNN-based models.
  arXiv  Detail & Related papers  (2022-02-02T04:49:14Z)
• Robust Self-Supervised Audio-Visual Speech Recognition [29.526786921769613]
  We present a self-supervised audio-visual speech recognition framework built upon Audio-Visual HuBERT (AV-HuBERT) On the largest available AVSR benchmark dataset LRS3, our approach outperforms prior state-of-the-art by 50% (28.0% vs. 14.1%) using less than 10% of labeled data. Our approach reduces the WER of an audio-based model by over 75% (25.8% vs. 5.8%) on average.
  arXiv  Detail & Related papers  (2022-01-05T18:50:50Z)
• Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation [51.37980448183019]
  We propose Audio ALBERT, a lite version of the self-supervised speech representation model. We show that Audio ALBERT is capable of achieving competitive performance with those huge models in the downstream tasks. In probing experiments, we find that the latent representations encode richer information of both phoneme and speaker than that of the last layer.
  arXiv  Detail & Related papers  (2020-05-18T10:42:44Z)
• NAViDAd: A No-Reference Audio-Visual Quality Metric Based on a Deep Autoencoder [0.0]
  We propose a No-Reference Audio-Visual Quality Metric Based on a Deep Autoencoder (NAViDAd) The model is formed by a 2-layer framework that includes a deep autoencoder layer and a classification layer. The model performed well when tested against the UnB-AV and the LiveNetflix-II databases.
  arXiv  Detail & Related papers  (2020-01-30T15:40:08Z)

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.