mlsanityData to 7 Oct 2026

DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction

arXiv 2310.04567 ↗First posted 6 Oct 2023eess.AS cs.SDcited by 12

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

Common target sound extraction (TSE) approaches primarily relied on discriminative approaches in order to separate the target sound while minimizing interference from the unwanted sources, with varying success in separating the target from the background. This study introduces DPM-TSE, a first generative method based on diffusion probabilistic modeling (DPM) for target sound extraction, to achieve both cleaner target renderings as well as improved separability from unwanted sounds. The technique also tackles common background noise issues with DPM by introducing a correction method for noise schedules and sample steps. This approach is evaluated using both objective and subjective quality metrics on the FSD Kaggle 2018 dataset. The results show that DPM-TSE has a significant improvement in perceived quality in terms of target extraction and purity.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 26 of its 35 references that are in the map. First posted on arXiv 6 Oct 2023.

Builds on

26 of 35 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Target Speech Extraction with Conditional Diffusion Model8 Aug
  2. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Models29 Jan
  3. 2022Diffusion-based Generative Speech Source Separation31 Oct
  4. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Models11 Aug
  5. 2022Conditional Diffusion Probabilistic Model for Speech Enhancement10 Feb
  6. 2021Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme28 Sep

Other references · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  4. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  5. 2018SDR - half-baked or well done?cited by 420
  6. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 400
  7. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
  8. 2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
  9. 2020ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metriccited by 76
  10. 2018A multi-device dataset for urban acoustic scene classificationcited by 75
  11. 2018VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Maskingcited by 72
  12. 2021Sound Event Detection: A Tutorialcited by 51
8 more
  1. 2021CDPAM: Contrastive learning for perceptual audio similaritycited by 42
  2. 2020Listen to What You Want: Neural Network-based Universal Sound Selectorcited by 27
  3. 2022Real-Time Target Sound Extractioncited by 22
  4. 2020Conditioned Source Separation for Music Instrument Performancescited by 18
  5. 2020One-shot conditional audio filtering of arbitrary soundscited by 18
  6. 2020Source separation with weakly labelled data: An approach to computational auditory scene analysiscited by 12
  7. 2022Improving Target Sound Extraction with Timestamp Informationcited by 10
  8. 2021Few-shot learning of new sound classes for target sound extractioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 5.

12 papers.

  1. 2024EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformercited by 30
  2. 2024FlowSep: Language-Queried Sound Separation with Rectified Flow Matchingcited by 21
  3. 2024SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformercited by 11
  4. 2025SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipelinecited by 9
  5. 2025MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Modelscited by 7
  6. 2024SoundMorpher: Perceptually-Uniform Sound Morphing with Diffusion Modelcited by 3
  7. 2026SAM Audio Judge: A Unified Multimodal Framework for Perceptual Evaluation of Audio Separationcited by 1
  8. 2026StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Modelcited by 1
  9. 2026FlowSep 2: Self-Supervised Flow Matching for Language-Queried Audio Source Separationcited by 1
  10. 2025Text-Queried Audio Source Separation via Hierarchical Modelingcited by 0
  11. 2026Fine-grained Soundscape Control for Augmented Hearingcited by 0
  12. 2026TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Reconstruction of Sound Field through Diffusion Models
  2. 2025High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling
  3. 2023DDTSE: Discriminative Diffusion Model for Target Speech Extraction
  4. 2025Adaptive Deterministic Flow Matching for Target Speaker Extraction
  5. 2024Cross-attention Inspired Selective State Space Models for Target Sound Extraction
  6. 2026Mask2Flow-TSE: Two-Stage Target Speaker Extraction with Masking and Flow Matching
  7. 2025Audio Generation Through Score-Based Generative Modeling: Design Principles and Implementation
  8. 2021A Study on Speech Enhancement Based on Diffusion Probabilistic Model