EnCodecMAE: Leveraging neural codecs for universal audio representation learning

• URL: http://arxiv.org/abs/2309.07391v2
• Date: Tue, 21 May 2024 00:39:47 GMT
• Title: EnCodecMAE: Leveraging neural codecs for universal audio representation learning
• Authors: Leonardo Pepino, Pablo Riera, Luciana Ferrer,
• Abstract summary: We propose masking representations of the audio signal, and training a MAE to reconstruct the masked segments. We evaluate this approach, which we call EnCodecMAE, on a wide range of tasks involving speech, music and environmental sounds.
• Score: 16.590638305972632
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The goal of universal audio representation learning is to obtain foundational models that can be used for a variety of downstream tasks involving speech, music and environmental sounds. To approach this problem, methods inspired by works on self-supervised learning for NLP, like BERT, or computer vision, like masked autoencoders (MAE), are often adapted to the audio domain. In this work, we propose masking representations of the audio signal, and training a MAE to reconstruct the masked segments. The reconstruction is done by predicting the discrete units generated by EnCodec, a neural audio codec, from the unmasked inputs. We evaluate this approach, which we call EnCodecMAE, on a wide range of tasks involving speech, music and environmental sounds. Our best model outperforms various state-of-the-art audio representation models in terms of global performance. Additionally, we evaluate the resulting representations in the challenging task of automatic speech recognition (ASR), obtaining decent results and paving the way for a universal audio representation.

Related papers

• AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes [6.375996974877916]
  We propose a method named AudioFormer, which learns audio feature representations through the acquisition of discrete acoustic codes. Our research outcomes demonstrate that AudioFormer attains significantly improved performance compared to prevailing monomodal audio classification models.
  arXiv  Detail & Related papers  (2023-08-14T15:47:25Z)
• A vector quantized masked autoencoder for audiovisual speech emotion recognition [5.8641712963450825]
  The paper proposes the VQ-MAE-AV model, a vector quantized masked autoencoder (MAE) designed for audiovisual speech self-supervised representation learning. A multimodal MAE with self- or cross-attention mechanisms is proposed to fuse the audio and visual speech modalities and to learn local and global representations of the audiovisual speech sequence. Experimental results show that the proposed approach, which is pre-trained on the VoxCeleb2 database and fine-tuned on standard emotional audiovisual speech datasets, outperforms the state-of-the-art audiovisual SER methods.
  arXiv  Detail & Related papers  (2023-05-05T14:19:46Z)
• Audiovisual Masked Autoencoders [93.22646144125457]
  We show that we can achieve significant improvements on audiovisual downstream classification tasks. We additionally demonstrate the transferability of our representations, achieving state-of-the-art audiovisual results on Epic Kitchens.
  arXiv  Detail & Related papers  (2022-12-09T17:34:53Z)
• LA-VocE: Low-SNR Audio-visual Speech Enhancement using Neural Vocoders [53.30016986953206]
  We propose LA-VocE, a new two-stage approach that predicts mel-spectrograms from noisy audio-visual speech via a transformer-based architecture. We train and evaluate our framework on thousands of speakers and 11+ different languages, and study our model's ability to adapt to different levels of background noise and speech interference.
  arXiv  Detail & Related papers  (2022-11-20T15:27:55Z)
• Contrastive Audio-Visual Masked Autoencoder [85.53776628515561]
  Contrastive Audio-Visual Masked Auto-Encoder (CAV-MAE) Our fully self-supervised pretrained CAV-MAE achieves a new SOTA accuracy of 65.9% on VGGSound.
  arXiv  Detail & Related papers  (2022-10-02T07:29:57Z)
• Learning Contextual Tag Embeddings for Cross-Modal Alignment of Audio and Tags [32.456824945999465]
  We propose a method for learning audio representations using an audio autoencoder (AAE), a general word embeddings model (WEM), and a multi-head self-attention mechanism. Our results show that employing multi-head self-attention with multiple heads in the tag-based network can induce better learned audio representations.
  arXiv  Detail & Related papers  (2020-10-27T10:13:17Z)
• Self-Supervised Learning of Audio-Visual Objects from Video [108.77341357556668]
  We introduce a model that uses attention to localize and group sound sources, and optical flow to aggregate information over time. We demonstrate the effectiveness of the audio-visual object embeddings that our model learns by using them for four downstream speech-oriented tasks.
  arXiv  Detail & Related papers  (2020-08-10T16:18:01Z)
• Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision [63.564385139097624]
  We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from audio) Our results demonstrate the potential of multimodal self-supervision in audiovisual speech for learning good audio representations.
  arXiv  Detail & Related papers  (2020-07-08T14:07:06Z)
• COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations [32.456824945999465]
  We propose a method for learning audio representations, aligning the learned latent representations of audio and associated tags. We evaluate the quality of our embedding model, measuring its performance as a feature extractor on three different tasks.
  arXiv  Detail & Related papers  (2020-06-15T13:17:18Z)
• Unsupervised Audiovisual Synthesis via Exemplar Autoencoders [59.13989658692953]
  We present an unsupervised approach that converts the input speech of any individual into audiovisual streams of potentially-infinitely many output speakers. We use Exemplar Autoencoders to learn the voice, stylistic prosody, and visual appearance of a specific target speech exemplar.
  arXiv  Detail & Related papers  (2020-01-13T18:56:45Z)

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.