Matching Text and Audio Embeddings: Exploring Transfer-learning Strategies for Language-based Audio Retrieval

• URL: http://arxiv.org/abs/2210.02833v1
• Date: Thu, 6 Oct 2022 11:45:14 GMT
• Title: Matching Text and Audio Embeddings: Exploring Transfer-learning Strategies for Language-based Audio Retrieval
• Authors: Benno Weck, Miguel P\'erez Fern\'andez, Holger Kirchhoff, Xavier Serra
• Abstract summary: We present an analysis of large-scale pretrained deep learning models used for cross-modal (text-to-audio) retrieval. We use embeddings extracted by these models in a metric learning framework to connect matching pairs of audio and text.
• Score: 11.161404854726348
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present an analysis of large-scale pretrained deep learning models used for cross-modal (text-to-audio) retrieval. We use embeddings extracted by these models in a metric learning framework to connect matching pairs of audio and text. Shallow neural networks map the embeddings to a common dimensionality. Our system, which is an extension of our submission to the Language-based Audio Retrieval Task of the DCASE Challenge 2022, employs the RoBERTa foundation model as the text embedding extractor. A pretrained PANNs model extracts the audio embeddings. To improve the generalisation of our model, we investigate how pretraining with audio and associated noisy text collected from the online platform Freesound improves the performance of our method. Furthermore, our ablation study reveals that the proper choice of the loss function and fine-tuning the pretrained models are essential in training a competitive retrieval system.

Related papers

• 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)
• Continual Learning for On-Device Speech Recognition using Disentangled Conformers [54.32320258055716]
  We introduce a continual learning benchmark for speaker-specific domain adaptation derived from LibriVox audiobooks. We propose a novel compute-efficient continual learning algorithm called DisentangledCL. Our experiments show that the DisConformer models significantly outperform baselines on general ASR.
  arXiv  Detail & Related papers  (2022-12-02T18:58:51Z)
• ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification [42.95038619688867]
  ASiT is a novel self-supervised learning framework that captures local and global contextual information by employing group masked model learning and self-distillation. We evaluate our pretrained models on both audio and speech classification tasks, including audio event classification, keyword spotting, and speaker identification.
  arXiv  Detail & Related papers  (2022-11-23T18:21:09Z)
• BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping [19.071463356974387]
  This work extends existing methods based on self-supervised learning by bootstrapping, proposes various encoder architectures, and explores the effects of using different pre-training datasets. We present a novel training framework to come up with a hybrid audio representation, which combines handcrafted and data-driven learned audio features. All the proposed representations were evaluated within the HEAR NeurIPS 2021 challenge for auditory scene classification and timestamp detection tasks.
  arXiv  Detail & Related papers  (2022-06-24T02:26:40Z)
• CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations [20.239063010740853]
  We present a Cross-modal Transformer for Audio-and-Language, i.e., CTAL, which aims to learn the intra-modality and inter-modality connections between audio and language. We observe significant improvements across various tasks, such as, emotion classification, sentiment analysis, and speaker verification.
  arXiv  Detail & Related papers  (2021-09-01T04:18:19Z)
• End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings [66.50782702086575]
  We present an end-to-end deep network model that performs meeting diarization from single-channel audio recordings. The proposed system is designed to handle meetings with unknown numbers of speakers, using variable-number permutation-invariant cross-entropy based loss functions.
  arXiv  Detail & Related papers  (2021-05-05T14:55:29Z)
• SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding [61.02342238771685]
  Spoken language understanding requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. Various pre-training methods have been proposed to learn rich representations from large-scale unannotated speech and text. We propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules.
  arXiv  Detail & Related papers  (2020-10-05T19:29:49Z)
• Unsupervised Cross-Modal Audio Representation Learning from Unstructured Multilingual Text [69.55642178336953]
  We present an approach to unsupervised audio representation learning. Based on a triplet neural network architecture, we harnesses semantically related cross-modal information to estimate audio track-relatedness. We show that our approach is invariant to the variety of annotation styles as well as to the different languages of this collection.
  arXiv  Detail & Related papers  (2020-03-27T07:37:15Z)
• Curriculum Audiovisual Learning [113.20920928789867]
  We present a flexible audiovisual model that introduces a soft-clustering module as the audio and visual content detector. To ease the difficulty of audiovisual learning, we propose a novel learning strategy that trains the model from simple to complex scene. We show that our localization model significantly outperforms existing methods, based on which we show comparable performance in sound separation without referring external visual supervision.
  arXiv  Detail & Related papers  (2020-01-26T07:08:47Z)

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.