Elamur Research⌕
☰
home / authors / Jinyu Li

Jinyu Li

Jinyu Li has 5 papers in our library, in 2020–2026, most of them on Language models & pretraining, Speech & spoken language, Reasoning; often with Shujie Liu, Long Zhou, Sanyuan Chen.

5 papers in our library · 2020–2026

OpenAlex · ORCID · Wikidata · h-index 53 · 315 works · 12,903 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 326 times in our library · 3 more in our library without a page yet · ⭐ Paper Stars ranking: #4543

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢MicrosoftRedmond · United States2007–2026 · 207 paperscurrent🔬Laboratoire de Phonétique et PhonologieParis · France2018–2026 · 6 paperscurrent🎓Université Sorbonne NouvelleParis · France2024–2026 · 2 paperscurrent🔬Centre National de la Recherche ScientifiqueParis · France2026 · 1 papercurrent🔬Savoirs, Textes, LangageVilleneuve-d'Ascq · France2026 · 1 papercurrent🎓Université de LilleLille · France2026 · 1 papercurrent🎓Georgia Institute of TechnologyAtlanta · United States2006–2009 · 7 papers🏢Microsoft ResearchCambridge · United Kingdom2021–2025 · 2 papers🎓Kunming Medical UniversityKunming · China2022 · 2 papers🏢IFlyTekHefei · China2004–2005 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 9 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 10The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 5 worksComputer Science · 5 worksArtificial Intelligence · 5 worksLanguage and Linguistics · 5 worksSignal Processing · 4 worksMedicine · 1 workPhysiology · 1 workPsychology · 1 workExperimental and Cognitive Psychology · 1 workComputer Vision and Pattern Recognition · 1 work

🧭 Topics 4Research subjects and languages the work is about.Speech & spoken language · 2 worksLanguage models & pretraining · 2 worksEfficient models & compression · 1 workReasoning · 1 work

 Works by year

2020s

20262 papers20251 paper20231 paper20201 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers (2023 · 335 citations)
    Zero-shot text-to-speech means reproducing a voice the system never saw during training. Earlier approaches relied on speaker adaptation or dedicated speaker encoders. Models trained on small, studio-clean corpora tend to generalize poorly to new speakers.
  2. Autoregressive Speech Synthesis without Vector Quantization (2025 · 25 citations)
    Codec-based zero-shot TTS systems such as VALL-E represent speech as vector-quantized tokens. These tokens lose fidelity compared with continuous features. Sampling from them can also produce silences or noise loops, and the systems need a two-pass AR+NAR decoder. MELLE removes quantization entirely: a single…
  3. SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026 · 3 citations)
    Judging how good synthetic speech sounds is still difficult. Common tools such as MOS ratings, A/B tests, or MCD produce a single number or a binary choice, which explains nothing about the judgment. Learned predictors such as UTMOS are usually limited to one task and one language. The authors propose…
  4. Closing the Modality Reasoning Gap for Speech Large Language Models (2026 · 2 citations)
    Speech LLMs, which pair a speech encoder and adapter with a text LLM, reason noticeably worse on spoken questions than on the same questions in text.
  5. Sequence-level self-learning with multiple hypotheses (2020)
    The paper addresses self-training for end-to-end speech recognition when untranscribed audio is the only adaptation material.

All works

8 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

  1. Restructuring of deep neural network acoustic models with singular value decomposition ↗Interspeech (USB) · no summary yetJian Xue, Jinyu Li, Yifan Gong2013 · 421 citations
  2. Neural Codec Language Models are Zero-Shot Text to Speech SynthesizersarXiv:2301.02111Chengyi Wang, Sanyuan Chen, Yu Wu, et al.2023 · 335 citations
  3. WavLLM: Towards Robust and Adaptive Speech Large Language Model ↗Findings of the Association for Computational Linguistics: EMNLP 2024 · no summary yetShujie Hu et al.2024 · 98 citations
  4. Autoregressive Speech Synthesis without Vector QuantizationAnnual Meeting of the Association for Computational Linguistics (ACL)Lingwei Meng, Long Zhou, Shujie Liu, et al.2025 · 25 citations
  5. SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality EvaluationAnnual Meeting of the Association for Computational Linguistics (ACL)Hui Wang, Jinghua Zhao, Yifan Yang, et al.2026 · 3 citations
  6. Closing the Modality Reasoning Gap for Speech Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Chaoren Wang, Heng Lu, Xueyao Zhang, et al.2026 · 2 citations
  7. Sequence-level self-learning with multiple hypothesesInterspeechKenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, et al.2020
  8. Production de la parole en réponse à de multiples perturbations du feedback auditif (Speech production in response to multiple perturbations of auditory feedback) ↗Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole · no summary yetJinyu Li, Leonardo Lancia2020

 Co-authors here

12 of 24 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 326 times (of the 149,439 papers whose bibliographies we read); 69 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jinyu-li/