Improving Text-To-Audio Models with Synthetic Captions

• URL: http://arxiv.org/abs/2406.15487v2
• Date: Mon, 8 Jul 2024 20:15:33 GMT
• Title: Improving Text-To-Audio Models with Synthetic Captions
• Authors: Zhifeng Kong, Sang-gil Lee, Deepanway Ghosal, Navonil Majumder, Ambuj Mehrish, Rafael Valle, Soujanya Poria, Bryan Catanzaro,
• Abstract summary: 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.
• Score: 51.19111942748637
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: It is an open challenge to obtain high quality training data, especially captions, for text-to-audio models. Although prior methods have leveraged \textit{text-only language models} to augment and improve captions, such methods have limitations related to scale and coherence between audio and captions. In this work, we propose an audio captioning pipeline that uses an \textit{audio 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 \texttt{AF-AudioSet}, and then evaluate the benefit of pre-training text-to-audio models on these synthetic captions. Through systematic evaluations on AudioCaps and MusicCaps, we find leveraging our pipeline and synthetic captions leads to significant improvements on audio generation quality, achieving a new \textit{state-of-the-art}.

Related papers

• Zero-shot audio captioning with audio-language model guidance and audio context keywords [59.58331215337357]
  We propose ZerAuCap, a novel framework for summarising general audio signals in a text caption without requiring task-specific training. Our framework exploits a pre-trained large language model (LLM) for generating the text which is guided by a pre-trained audio-language model to produce captions. Our proposed framework achieves state-of-the-art results in zero-shot audio captioning on the AudioCaps and Clotho datasets.
  arXiv  Detail & Related papers  (2023-11-14T18:55:48Z)
• Zero-Shot Audio Captioning via Audibility Guidance [57.70351255180495]
  We propose three desiderata for captioning audio -- (i) fluency of the generated text, (ii) faithfulness of the generated text to the input audio, and (iii) audibility. Our method is a zero-shot method, i.e., we do not learn to perform captioning. We present our results on the AudioCap dataset, demonstrating that audibility guidance significantly enhances performance compared to the baseline.
  arXiv  Detail & Related papers  (2023-09-07T17:45:58Z)
• Exploring the Role of Audio in Video Captioning [59.679122191706426]
  We present an audio-visual framework, which aims to fully exploit the potential of the audio modality for captioning. We propose new local-global fusion mechanisms to improve information exchange across audio and video.
  arXiv  Detail & Related papers  (2023-06-21T20:54:52Z)
• CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models [50.42886595228255]
  We propose to learn the desired text-audio correspondence by leveraging the visual modality as a bridge. We train a conditional diffusion model to generate the audio track of a video, given a video frame encoded by a pretrained contrastive language-image pretraining model.
  arXiv  Detail & Related papers  (2023-06-16T05:42:01Z)
• 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)
• Audio Captioning with Composition of Acoustic and Semantic Information [1.90365714903665]
  We present a novel encoder-decoder architecture using bi-directional Gated Recurrent Units (BiGRU) with audio and semantic embeddings. To extract audio features, we use the log Mel energy features, VGGish embeddings, and a pretrained audio neural network (PANN) embeddings. Our proposed model outperforms state-of-the-art audio captioning models across different evaluation metrics.
  arXiv  Detail & Related papers  (2021-05-13T15:30:14Z)
• Audio Captioning using Gated Recurrent Units [1.3960152426268766]
  VGGish audio embedding model is used to explore the usability of audio embeddings in the audio captioning task. The proposed architecture encodes audio and text input modalities separately and combines them before the decoding stage. Our experimental results show that the proposed BiGRU-based deep model outperforms the state of the art results.
  arXiv  Detail & Related papers  (2020-06-05T12:03:12Z)

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.