Speech-processing researcher probing emotion recognition and end-of-turn detection in conversational AI systems
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
0
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—
Output data is insufficient: this OpenAlex record carries no populated publication or citation totals beyond yearly work counts, so this axis would measure total and per-year scholarly output volume; it cannot yet be scored.
Impact—
Impact cannot be assessed: h-index and citation data are not populated for this OpenAlex record, so this axis would measure citation-based influence and uptake of the work; no score is estimated.
Focus0/100
Focus scores 0/100, reflecting an even field split: the field distribution divides exactly 50/50 between speech processing (conversational AI) and speech processing / affective computing (NLP). Topic assignments, however, stay speech-centric — speech recognition and synthesis (9), speech and dialogue systems (7), and speech and audio processing (6) dominate, with topic modeling (4) and NLP techniques (1) as minor threads.
Collaboration44/100
Collaboration scores 44/100, based on 8 distinct coauthors in the recent record. The frequent-coauthor list centers on established speech researchers — Andreas Stolcke, Petr Motlicek, Esa'u Villatoro-Tello, Sergio Burdisso, Rini Sharon, Hasindri Watawana, Manickavela A, and Manjunath K E — indicating work inside seasoned teams. Both reviewed 2026 papers place the researcher in middle author positions without corresponding credit.
Activity70/100
Activity scores 70/100. The record shows 10 works in the last three years with a sharp ramp: 1 work in 2024, 1 in 2025, and 8 in 2026, so nearly all indexed output sits in the most recent year. The two Evolve-reviewed papers are both 2026 arXiv preprints, corroborating a strongly accelerating current publication pace.
Reproducibility38/100
Reproducibility scores 38/100, computed from Evolve's review of 2 papers (mean readiness 38). The SpeechLLM emotion-recognition study is rated medium readiness — a linear head on frozen hidden states aids replication, though it uses a single corpus and lacks significance tests. The end-of-turn ablation is rated low readiness, with proprietary single-domain data limiting external replication.
Research summary
Kadri Hacioglu is a speech-processing researcher whose profile is name-resolved from OpenAlex bibliographic data; no institution, country, or ORCID is attached to this record. The evidence describes a contributor at the intersection of conversational speech AI and affective computing: the field distribution splits exactly 50/50 between speech processing (conversational AI) and speech processing / affective computing (NLP). Topic assignments concentrate on speech recognition and synthesis (9 works), speech and dialogue systems (7), and speech and audio processing (6), with smaller clusters in topic modeling (4) and NLP techniques (1). Publication activity is recent and accelerating — 1 work in 2024, 1 in 2025, and 8 in 2026, for 10 works in the last three years — yielding an activity score of 70 against a collaboration score of 44 (8 distinct coauthors). Evolve has reviewed two 2026 arXiv papers: a discriminative-adaptation study of SpeechLLMs for speech emotion recognition on IEMOCAP, and an ablation of acoustic, prosodic, and textual cues for end-of-turn detection. Reproducibility readiness averages 38 across the two reviews. Citation-based output and impact scores are unavailable, so this should be read as an early-stage profile grounded in bibliographic metadata rather than citation impact.
Collaboration pattern
Co-authorship is moderate: 8 distinct coauthors in the recent record, forming a stable recurring circle — Andreas Stolcke, Petr Motlicek, Esa'u Villatoro-Tello, Sergio Burdisso, Rini Sharon, Hasindri Watawana, Manickavela A, and Manjunath K E. Both reviewed 2026 papers sit in middle author positions without corresponding credit, suggesting a contributor role within established speech-research teams rather than an independent group lead. No affiliation is attached, so team boundaries are inferred from co-authorship only.
Research keywords
Highlights
Discriminative adaptation of SpeechLLMs for emotion recognition
Ablating which speech cues drive end-of-turn detection
Timeline
- 2024First indexed work appears in the OpenAlex record (1 work).
- 2025Output stays minimal, with 1 indexed work.
- 2026Publication surge: 8 indexed works, bringing the three-year total to 10.
- 2026Two arXiv preprints are reviewed by Evolve: SpeechLLM-based emotion recognition and an end-of-turn detection ablation.
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 are computed from OpenAlex only; no ORCID, institution, or country is attached, and identity is name-resolved from public bibliographic data.
- Citation-based output and impact metrics (h-index, i10-index, citation counts) are not populated, so those radar axes are left unscored.
- Only 2 papers carry Evolve reviews; other indexed works are not individually assessed.
- Both reviewed papers are 2026 arXiv preprints in middle author positions; peer-reviewed venue status is not captured in this data.