Early-career speech AI researcher at Jilin Medical University working on non-verbal ASR and full-duplex dialogue agents
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
6
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Not yet scored: this snapshot lacks sufficient citation-linked publication data to measure cumulative output volume and per-year productivity consistency, so no estimate is made. The only volume signals available are the raw yearly counts, which climb from 1–2 works (2018–2024) to 14 in 2026.
Impact—
Not yet scored: citation counts and field-normalized influence measures are absent from this snapshot, so impact cannot be estimated. This axis would capture how often the work is cited and adopted by others — for example, uptake of the NVVSpeech ASR system and the Gander duplex agent.
Focus0/100
The focus score is 0, driven by the field distribution: output splits exactly 50/50 between speech processing / computational paralinguistics and speech-and-multimodal machine learning for spoken dialogue systems. Topic counts confirm breadth over concentration — Speech Recognition and Synthesis (13), Speech and Dialogue Systems (13), Speech and Audio Processing (7), Action Observation and Synchronization (7), and Neural and Behavioral Psychology Studies (4) — pointing to two parallel research lines rather than one narrow specialty.
Collaboration70/100
Collaboration scores 70, backed by 32 distinct coauthors across 22 works in the recent three-year window — a broad, team-based pattern. The frequent-coauthor list spans Shangyue Jia, Jingru Ma, Daoping Luo, Bowen Tian, Hanchen Lu, Wenze Ren, Yunxiang Chen, Houdun Liu, Su Feng, Lei Xie, Liumeng Xue, and Orantqing, suggesting stable speech-technology project teams; both catalog papers are middle-author, non-corresponding contributions.
Activity91/100
Activity is the strongest axis at 91: the snapshot records 22 works in the last three years, with yearly counts accelerating sharply — from 1–2 per year across 2018–2024 to 6 in 2025 and 14 in 2026. Both reviewed catalog papers are dated 2026, consistent with an intensive current push into challenge-driven ASR and full-duplex dialogue systems.
Reproducibility55/100
Reproducibility sits at a moderate 55, computed from 2 assessed papers (reproMean 55); both catalog entries carry a medium repro-readiness rating. The NVVSpeech system paper reports a Track 1 rank-4 result (63.86), though Evolve's review flags an unexplained local-versus-official score gap and thin statistics as reproducibility caveats.
Research summary
Yangzhuo Li (Jilin Medical University, China; ORCID 0000-0003-4450-2849) is an early-stage researcher working on speech technology, with the OpenAlex field distribution split evenly — 0.5/0.5 — between speech processing / computational paralinguistics and speech and multimodal machine learning for spoken dialogue systems. Topic counts reinforce that breadth: Speech Recognition and Synthesis and Speech and Dialogue Systems lead with 13 each, followed by Speech and Audio Processing (7), Action Observation and Synchronization (7), and Neural and Behavioral Psychology Studies (4). Activity is the clearest signal: 22 works in the last three years, with yearly output climbing from 1–2 publications (2018–2024) to 6 in 2025 and 14 in 2026. Collaboration is broad, with 32 distinct coauthors in the recent window (collaboration score 70); recurring partners include Shangyue Jia, Jingru Ma, Lei Xie, and Liumeng Xue. Two 2026 arXiv system papers are reviewed in the Evolve catalog: a long-tail rebalancing system for non-verbal vocalization-aware ASR that placed 4th in NVVSpeech Challenge Track 1 (63.86), and Gander, a multimodal duplex interaction agent with the strongest turn-taking (100%/8.0%) but last-place task accuracy on its main benchmark. Reproducibility is moderate (mean 55 across 2 assessed papers). Citation-based output and impact are left unscored; the snapshot lists an h-index of 6 and i10 index of 5.
Collaboration pattern
Yangzhuo Li works in sizeable project teams: 32 distinct coauthors appear across 22 works in the recent three-year window, and the collaboration score is 70. The recurring-coauthor list is led by Shangyue Jia, Jingru Ma, Daoping Luo, Bowen Tian, Hanchen Lu, Wenze Ren, Yunxiang Chen, Houdun Liu, Su Feng, Lei Xie, Liumeng Xue, and Orantqing. Both catalog papers are middle-position, non-corresponding contributions, consistent with a collaborative contributor role rather than sole leadership.
Research keywords
Highlights
NVVSpeech Challenge Track 1: rank 4 via long-tail rebalancing
Gander: full-duplex speech agent with leading turn-taking
Timeline
- 2018First indexed work appears in the OpenAlex counts-by-year record (1 publication); output stays sparse, at 1–2 works per year, through 2024.
- 2021Sparse early output continues, with 1 indexed publication in 2021.
- 2023Output ticks up to 2 indexed publications, hinting at the start of a steadier rhythm.
- 2025Activity accelerates: 6 indexed publications in 2025, the strongest year to that point.
- 2026Busiest year on record with 14 works; two arXiv system papers from this year were reviewed by Evolve — the NVVSpeech Challenge Track 1 ASR entry (rank 4, 63.86) and the Gander full-duplex interaction agent.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometrics come from a single OpenAlex snapshot (identity: openalex); citation-based output and impact axes are unscored because coverage is insufficient, and only the small raw h-index (6) and i10 index (5) are on record.
- Only 2 papers by this researcher have been reviewed in the Evolve catalog; the broader corpus is summarized through aggregate topic and field counts only.
- This profile is name-resolved from public bibliographic data (ORCID 0000-0003-4450-2849); same-name disambiguation beyond that record has not been independently verified.
- The reproducibility score rests on only 2 assessed papers (mean 55), too small a base for a strong claim.