Text-Queried Audio Source Separation via Hierarchical Modeling

• URL: http://arxiv.org/abs/2505.21025v1
• Date: Tue, 27 May 2025 11:00:38 GMT
• Title: Text-Queried Audio Source Separation via Hierarchical Modeling
• Authors: Xinlei Yin, Xiulian Peng, Xue Jiang, Zhiwei Xiong, Yan Lu,
• Abstract summary: We propose a hierarchical decomposition framework, HSM-TSS, that decouples the task into global-local semantic-guided feature separation and structure-preserving acoustic reconstruction.<n>A Q-Audio architecture is employed to align audio and text modalities, serving as pretrained global-semantic encoders.<n>Our method achieves state-of-the-art separation performance with data-efficient training while maintaining superior semantic consistency with queries in complex auditory scenes.
• Score: 53.94434504259829
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Target audio source separation with natural language queries presents a promising paradigm for extracting arbitrary audio events through arbitrary text descriptions. Existing methods mainly face two challenges, the difficulty in jointly modeling acoustic-textual alignment and semantic-aware separation within a blindly-learned single-stage architecture, and the reliance on large-scale accurately-labeled training data to compensate for inefficient cross-modal learning and separation. To address these challenges, we propose a hierarchical decomposition framework, HSM-TSS, that decouples the task into global-local semantic-guided feature separation and structure-preserving acoustic reconstruction. Our approach introduces a dual-stage mechanism for semantic separation, operating on distinct global and local semantic feature spaces. We first perform global-semantic separation through a global semantic feature space aligned with text queries. A Q-Audio architecture is employed to align audio and text modalities, serving as pretrained global-semantic encoders. Conditioned on the predicted global feature, we then perform the second-stage local-semantic separation on AudioMAE features that preserve time-frequency structures, followed by acoustic reconstruction. We also propose an instruction processing pipeline to parse arbitrary text queries into structured operations, extraction or removal, coupled with audio descriptions, enabling flexible sound manipulation. Our method achieves state-of-the-art separation performance with data-efficient training while maintaining superior semantic consistency with queries in complex auditory scenes.

Related papers

• Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics [26.399212357764576]
  We propose Dynamic Derivation and Elimination (DDESeg): a novel audio-visual segmentation framework.<n>To mitigate feature confusion, DDESeg reconstructs the semantic content of the mixed audio signal.<n>To reduce the matching difficulty, we introduce a discriminative feature learning module.
  arXiv  Detail & Related papers  (2025-03-17T05:38:05Z)
• SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation [10.828717295018123]
  We propose a unified embedding framework that eliminates the need for intermediate text representations.<n>Our model reduces pipeline latency by 50% while achieving higher retrieval accuracy compared to traditional two-stage methods.
  arXiv  Detail & Related papers  (2025-01-26T15:04:02Z)
• QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition [47.103732403296654]
  Multi-source semantic space can be represented as the Cartesian product of single-source sub-spaces. We introduce a global-to-local quantization mechanism, which distills knowledge from stable global (clip-level) features into local (frame-level) ones. Experiments demonstrate that our semantically decomposed audio representation significantly improves AVS performance.
  arXiv  Detail & Related papers  (2023-09-29T20:48:44Z)
• Learning Speech Representation From Contrastive Token-Acoustic Pretraining [57.08426714676043]
  We propose "Contrastive Token-Acoustic Pretraining (CTAP)", which uses two encoders to bring phoneme and speech into a joint multimodal space. The proposed CTAP model is trained on 210k speech and phoneme pairs, achieving minimally-supervised TTS, VC, and ASR.
  arXiv  Detail & Related papers  (2023-09-01T12:35:43Z)
• TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision [61.186488081379]
  We propose TextFormer, a query-based end-to-end text spotter with Transformer architecture. TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multi-task modeling. It allows for mutual training and optimization of classification, segmentation, and recognition branches, resulting in deeper feature sharing.
  arXiv  Detail & Related papers  (2023-06-06T03:37:41Z)
• Analysis of Joint Speech-Text Embeddings for Semantic Matching [3.6423306784901235]
  We study a joint speech-text embedding space trained for semantic matching by minimizing the distance between paired utterance and transcription inputs. We extend our method to incorporate automatic speech recognition through both pretraining and multitask scenarios.
  arXiv  Detail & Related papers  (2022-04-04T04:50:32Z)
• FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention [66.77490220410249]
  We propose FragmentVC, in which the latent phonetic structure of the utterance from the source speaker is obtained from Wav2Vec 2.0. FragmentVC is able to extract fine-grained voice fragments from the target speaker utterance(s) and fuse them into the desired utterance. This approach is trained with reconstruction loss only without any disentanglement considerations between content and speaker information.
  arXiv  Detail & Related papers  (2020-10-27T09:21:03Z)
• 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)
• Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning [31.7865837105092]
  We propose a novel training method that enables pretrained contextual embeddings to process acoustic features. We extend it with an encoder of pretrained speech recognition systems in order to construct end-to-end spoken language understanding systems.
  arXiv  Detail & Related papers  (2020-07-03T17:43:12Z)
• 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)

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.