Universal Sound Separation with Self-Supervised Audio Masked Autoencoder

• URL: http://arxiv.org/abs/2407.11745v2
• Date: Wed, 6 Nov 2024 17:52:55 GMT
• Title: Universal Sound Separation with Self-Supervised Audio Masked Autoencoder
• Authors: Junqi Zhao, Xubo Liu, Jinzheng Zhao, Yi Yuan, Qiuqiang Kong, Mark D. Plumbley, Wenwu Wang,
• Abstract summary: We propose integrating a self-supervised pre-trained model, namely the audio masked autoencoder (A-MAE), into a universal sound separation system. The proposed methods successfully enhance the separation performance of a state-of-the-art ResUNet-based USS model.
• Score: 35.560261097213846
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Universal sound separation (USS) is a task of separating mixtures of arbitrary sound sources. Typically, universal separation models are trained from scratch in a supervised manner, using labeled data. Self-supervised learning (SSL) is an emerging deep learning approach that leverages unlabeled data to obtain task-agnostic representations, which can benefit many downstream tasks. In this paper, we propose integrating a self-supervised pre-trained model, namely the audio masked autoencoder (A-MAE), into a universal sound separation system to enhance its separation performance. We employ two strategies to utilize SSL embeddings: freezing or updating the parameters of A-MAE during fine-tuning. The SSL embeddings are concatenated with the short-time Fourier transform (STFT) to serve as input features for the separation model. We evaluate our methods on the AudioSet dataset, and the experimental results indicate that the proposed methods successfully enhance the separation performance of a state-of-the-art ResUNet-based USS model.

Related papers

• Exploring Federated Self-Supervised Learning for General Purpose Audio Understanding [14.468870364990291]
  We propose a novel Federated SSL (F-SSL) framework, dubbed FASSL, that enables learning intermediate feature representations from large-scale decentralized heterogeneous clients. Our study has found that audio F-SSL approaches perform on par with the centralized audio-SSL approaches on the audio-retrieval task.
  arXiv  Detail & Related papers  (2024-02-05T10:57:48Z)
• TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition [51.565319173790314]
  TokenSplit is a sequence-to-sequence encoder-decoder model that uses the Transformer architecture. We show that our model achieves excellent performance in terms of separation, both with or without transcript conditioning. We also measure the automatic speech recognition (ASR) performance and provide audio samples of speech synthesis to demonstrate the additional utility of our model.
  arXiv  Detail & Related papers  (2023-08-21T01:52:01Z)
• Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding [57.08832099075793]
  Visually-guided sound source separation consists of three parts: visual feature extraction, multimodal feature fusion, and sound signal processing. This paper presents audio-visual predictive coding (AVPC) to tackle this task in parameter harmonizing and more effective manner. In addition, we develop a valid self-supervised learning strategy for AVPC via co-predicting two audio-visual representations of the same sound source.
  arXiv  Detail & Related papers  (2023-06-19T03:10:57Z)
• Anomalous Sound Detection using Audio Representation with Machine ID based Contrastive Learning Pretraining [52.191658157204856]
  This paper uses contrastive learning to refine audio representations for each machine ID, rather than for each audio sample. The proposed two-stage method uses contrastive learning to pretrain the audio representation model. Experiments show that our method outperforms the state-of-the-art methods using contrastive learning or self-supervised classification.
  arXiv  Detail & Related papers  (2023-04-07T11:08:31Z)
• Multi-Dimensional and Multi-Scale Modeling for Speech Separation Optimized by Discriminative Learning [9.84949849886926]
  Intra-SE-Conformer and Inter-Transformer (ISCIT) for speech separation. New network SE-Conformer can model audio sequences in multiple dimensions and scales.
  arXiv  Detail & Related papers  (2023-03-07T08:53:20Z)
• BEATs: Audio Pre-Training with Acoustic Tokenizers [77.8510930885778]
  Self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. We propose BEATs, an iterative audio pre-training framework to learn Bidirectional representation from Audio Transformers. In the first iteration, we use random projection as the acoustic tokenizer to train an audio SSL model in a mask and label prediction manner. Then, we train an acoustic tokenizer for the next iteration by distilling the semantic knowledge from the pre-trained or fine-tuned audio SSL model.
  arXiv  Detail & Related papers  (2022-12-18T10:41:55Z)
• SLICER: Learning universal audio representations using low-resource self-supervised pre-training [53.06337011259031]
  We present a new Self-Supervised Learning approach to pre-train encoders on unlabeled audio data. Our primary aim is to learn audio representations that can generalize across a large variety of speech and non-speech tasks.
  arXiv  Detail & Related papers  (2022-11-02T23:45:33Z)
• Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data [26.058278155958668]
  We propose a three-component pipeline to train a universal audio source separator from a large, but weakly-labeled dataset: AudioSet. Our approach uses a single model for source separation of multiple sound types, and relies solely on weakly-labeled data for training. The proposed audio separator can be used in a zero-shot setting, learning to separate types of audio sources that were never seen in training.
  arXiv  Detail & Related papers  (2021-12-15T05:13:43Z)
• 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)
• Audio-Visual Decision Fusion for WFST-based and seq2seq Models [3.2771898634434997]
  Under noisy conditions, speech recognition systems suffer from high Word Error Rates (WER) We propose novel methods to fuse information from audio and visual modalities at inference time. We show that our methods give significant improvements over acoustic-only WER.
  arXiv  Detail & Related papers  (2020-01-29T13:45:08Z)

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.