mlsanityData to 7 Oct 2026

High-Fidelity Speech Enhancement via Discrete Audio Tokens

arXiv 2510.02187 ↗First posted 2 Oct 2025cs.SD cs.LG eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

Recent autoregressive transformer-based speech enhancement (SE) methods have shown promising results by leveraging advanced semantic understanding and contextual modeling of speech. However, these approaches often rely on complex multi-stage pipelines and low sampling rate codecs, limiting them to narrow and task-specific speech enhancement. In this work, we introduce DAC-SE1, a simplified language model-based SE framework leveraging discrete high-resolution audio representations; DAC-SE1 preserves fine-grained acoustic details while maintaining semantic coherence. Our experiments show that DAC-SE1 surpasses state-of-the-art autoregressive SE methods on both objective perceptual metrics and in a MUSHRA human evaluation. We release our codebase and model checkpoints to support further research in scalable, unified, and high-quality speech enhancement.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 38 references that are in the map. First posted on arXiv 2 Oct 2025.

Builds on

34 of 38 references.

References · 34

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Segment Anythingcited by 8,158
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  7. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  8. 2022High Fidelity Neural Audio Compressioncited by 673
  9. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 611
  10. 2023Simple and Controllable Music Generationcited by 480
  11. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
  12. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 400
22 more
  1. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 400
  2. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 235
  3. 2020Real Time Speech Enhancement in the Waveform Domaincited by 183
  4. 2019WHAM!: Extending Speech Separation to Noisy Environmentscited by 154
  5. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 133
  6. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 109
  7. 2018A multi-device dataset for urban acoustic scene classificationcited by 75
  8. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 69
  9. 2023ICASSP 2023 Deep Noise Suppression Challengecited by 62
  10. 2021VoiceFixer: Toward General Speech Restoration with Neural Vocodercited by 50
  11. 2024SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metricscited by 38
  12. 2023SELM: Speech Enhancement Using Discrete Tokens and Language Modelscited by 36
  13. 2020An Open source Implementation of ITU-T Recommendation P.808 with Validationcited by 27
  14. 2024MaskSR: Masked Language Model for Full-band Speech Restorationcited by 24
  15. 2025LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancementcited by 19
  16. 2025HiFiTTS-2: A Large-Scale High Bandwidth Speech Datasetcited by 10
  17. 2023TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 DNS Challengecited by 8
  18. 2023PLCMOS -- a data-driven non-intrusive metric for the evaluation of packet loss concealment algorithmscited by 7
  19. 2022INTERSPEECH 2022 Audio Deep Packet Loss Concealment Challengecited by 6
  20. 2023The NPU-Elevoc Personalized Speech Enhancement System for ICASSP2023 DNS Challengecited by 4
  21. 2024BS-PLCNet: Band-split Packet Loss Concealment Network with Multi-task Learning Framework and Multi-discriminatorscited by 4
  22. 2025UniFlow: Unifying Speech Front-End Tasks via Continuous Generative Modelingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Absorbing Discrete Diffusion for Speech Enhancementcited by 0
  2. 2026Rethinking Language Model-Based Generative Speech Enhancement in the Latent Space of a Neural Audio Codeccited by 0