Lune

Profiles2023-2026

Xie Chen

Shanghai Innovation Institute

16Papers
11Last author
13Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers16

  1. MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean FlowsAuthor 6 of 6ACL 2026 · 25 citations
  2. SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream QuantizationAuthor 12 of 12ACL 2026 · 10 citations
  3. Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-trainingAuthor 11 of 11ACL 2026 · 4 citations
  4. FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio PretrainingAuthor 7 of 7ACL 2026 · 2 citations
  5. WaveEx: Accelerating Flow Matching-based Speech Generation via Wavelet-guided ExtrapolationAuthor 7 of 7AAAI 2026 · 1 citation
  6. ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech SynthesisAuthor 6 of 6ACL Findings 2026
  7. Speech Recognition Meets Large Language Model: Benchmarking, Models, and ExplorationAuthor 11 of 11AAAI 2025 · 17 citations
  8. SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage TrainingAuthor 16 of 16ACL Findings 2025 · 7 citations
  9. URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue ModelsAuthor 8 of 8EMNLP Findings 2025 · 7 citations
  10. Bitrate-Controlled Diffusion for Disentangling Motion and Content in VideoAuthor 5 of 6ICCV 2025 · 1 citation
  11. F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow MatchingAuthor 8 of 8ACL 2025
  12. GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and RefinementAuthor 16 of 19ACL 2025
  13. MUZO: Leveraging Multiple Queries and Momentum for Zeroth-Order Fine-Tuning of Large Language ModelsAuthor 4 of 4EMNLP 2025
  14. UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and VocodingAuthor 6 of 9AAAI 2024 · 64 citations
  15. AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion EncodingAuthor 3 of 4ACM MM 2024 · 19 citations
  16. DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion AutoencoderAuthor 5 of 9ACM MM 2023 · 36 citations
Dusk over the sea between two cliffs drawn in fine vertical lines