mlsanityData to 7 Oct 2026

LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models

arXiv 2504.07402 ↗First posted 10 Apr 2025cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

We propose LauraTSE, an Auto-Regressive Decoder-Only Language Model for Target Speaker Extraction built upon the LauraGPT backbone. LauraTSE employs a small-scale auto-regressive decoder-only language model that generates the initial layers of the target speech's discrete codec representations from the continuous embeddings of both the mixture and reference speech. These outputs serve as coarse-grained predictions. To refine them, a one-step encoder-only language model reconstructs the full codec representation by integrating information from both the mixture and the reference speech, adding fine-grained details. Experimental results show that our approach can achieve promising performance. Additionally, we conduct ablation studies to investigate the data scalability and the contribution of the encoder-only model.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

37 of 46 references.

References · 37

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  4. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  6. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  7. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 400
  8. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 230
  9. 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 189
  10. 2020Attention is All You Need in Speech Separationcited by 184
  11. 2021DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressorscited by 165
  12. 2020LibriMix: An Open-Source Dataset for Generalizable Speech Separationcited by 154
25 more
  1. 2022Conditional Diffusion Probabilistic Model for Speech Enhancementcited by 132
  2. 2022Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkitcited by 92
  3. 2023LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPTcited by 77
  4. 2023SpeechX: Neural Codec Language Model as a Versatile Speech Transformercited by 64
  5. 2023FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codeccited by 44
  6. 2024SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metricscited by 38
  7. 2023SELM: Speech Enhancement Using Discrete Tokens and Language Modelscited by 36
  8. 2020SpEx+: A Complete Time Domain Speaker Extraction Networkcited by 33
  9. 2023Neural Target Speech Extraction: An Overviewcited by 33
  10. 2024DASB - Discrete Audio and Speech Benchmarkcited by 32
  11. 2021Variational Autoencoder for Speech Enhancement with a Noise-Aware Encodercited by 28
  12. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  13. 2024How Should We Extract Discrete Audio Tokens from Self-Supervised Models?cited by 24
  14. 2025AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancementcited by 23
  15. 2019Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modelingcited by 21
  16. 2025LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancementcited by 19
  17. 2023Target Speech Extraction with Conditional Diffusion Modelcited by 15
  18. 2024Decoder-only Architecture for Streaming End-to-end Speech Recognitioncited by 12
  19. 2024TSELM: Target Speaker Extraction using Discrete Tokens and Language Modelscited by 10
  20. 2023TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognitioncited by 8
  21. 2024WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extractioncited by 8
  22. 2024SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modelingcited by 5
  23. 2024USEF-TSE: Universal Speaker Embedding Free Target Speaker Extractioncited by 5
  24. 2023Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillationcited by 4
  25. 2023Conditional Diffusion Model for Target Speaker Extractioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancementcited by 4
  2. 2025SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancementcited by 3
  3. 2025GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Modelcited by 1
  4. 2026StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Modelcited by 1
  5. 2026Breaking the Quality--Intelligibility Trade-off in Streaming Target Speaker Extraction via Deep-Feature-Anchored Preference Optimizationcited by 0