Jon Barker

University of Sheffield · United Kingdom

Unclaimed · AI-structured profileOpenAlex

Speech processing researcher at Sheffield advancing conversational speech enhancement for hearing-impaired listeners

papers here

reviewed by Evolve

first-author

corresponding

—

works · OpenAlex

h-index · OpenAlex

Bibliometric figures come from OpenAlex (2026-10-02) 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—

This axis measures publication volume and productivity over time. The underlying per-year output counts are not yet available in the current snapshot, so no score is reported and none is estimated here.

Impact—

This axis measures citation-based influence, such as citations per paper and h-index-type aggregates. The snapshot lacks usable citation data for this researcher, so impact is left unscored rather than guessed.

Focus0/100

The focus axis scores 0/100 in the current snapshot. The field distribution is split evenly — 'speech processing' at 0.5 and 'speech and audio signal processing (computational hearing)' at 0.5 — and the topic list spans five areas from speech recognition and synthesis to emotion recognition and few-shot learning, which the metric reads as low concentration, even though the two reviewed papers converge tightly on conversational speech enhancement and hearing aids.

Collaboration44/100

Collaboration scores 44/100. The recent three-year window records 8 distinct co-authors across 5 works, and frequent co-authors include Robert Sutherland, Stefan Goetze, Thomas Kuebert, Marko Lugger, Stefan Petrausch, Eline Borch Petersen, Juan Azcarreta Ortiz, and Buye Xu. Both Evolve-reviewed papers place Jon Barker in the last-author position without corresponding authorship, a pattern consistent with senior or supervisory roles on challenge-style team papers.

Activity52/100

Activity scores 52/100. OpenAlex attributes 5 works to the recent three-year window, and the counts-by-year record contains a single entry: 5 works in 2026. Both Evolve-reviewed papers appeared on arXiv in 2026. A one-year window limits trend reading, but the 2026 clustering suggests a currently active period centered on the CHiME-9 ECHI challenge cycle.

Reproducibility55/100

Reproducibility scores 55/100, computed as the mean readiness over 2 evaluated papers. Both Evolve-reviewed papers are rated 'medium' reproducibility: the CHiME-9 ECHI challenge paper rests on rigorous real-data subjective evaluation, while the multi-speaker extraction study reports concrete metric movement (STOI 0.55 to 0.60) yet evaluates speech quality only.

Research summary

This profile describes Jon Barker of the University of Sheffield (GB), name-resolved from OpenAlex bibliographic data. The record is concentrated in speech processing and in speech and audio signal processing with a computational-hearing emphasis, each accounting for 50% of the classified field distribution. Listed topics include Speech Recognition and Synthesis (3 works), Emotion and Mood Recognition (2), Hearing Loss and Rehabilitation, Speech and Audio Processing, and Domain Adaptation and Few-Shot Learning. OpenAlex attributes 5 works to the recent three-year window, all recorded in 2026, with 8 distinct co-authors. Two 2026 arXiv papers reviewed by Evolve anchor the qualitative picture, both in last-author position: the CHiME-9 ECHI challenge on enhancing conversations for hearing impairment, praised for rigorous real-data subjective evaluation, and a multi-speaker extraction study introducing a randomly VAD-masked loss that lifts STOI from 0.55 to 0.60 on real conversations. Recurring co-authors include Robert Sutherland, Stefan Goetze, Thomas Kuebert, Marko Lugger, Stefan Petrausch, Eline Borch Petersen, Juan Azcarreta Ortiz, and Buye Xu. Citation-based output and impact scores are unavailable in the current snapshot and are treated as unknown.

Collaboration pattern

Jon Barker's recent pattern is team-based: 8 distinct co-authors across 5 recent works (collaboration score 44/100), with both Evolve-reviewed 2026 papers in last-author, non-corresponding position — typical of senior involvement in challenge-style consortium papers. Recurring co-authors include Robert Sutherland, Stefan Goetze, Thomas Kuebert, Marko Lugger, Stefan Petrausch, Eline Borch Petersen, Juan Azcarreta Ortiz, and Buye Xu; both papers sit in the CHiME-9 ECHI ecosystem, suggesting a sustained challenge-oriented collaboration network.

Research keywords

Speech enhancementTarget speaker extractionMulti-speaker extractionConversational speech enhancementHearing aidsSpeech intelligibilityHearing loss and rehabilitationCHiME-9 ECHI challengeSpeech recognition and synthesisEmotion and mood recognitionDomain adaptation and few-shot learning

Highlights

CHiME-9 ECHI: community machine-learning challenge on enhancing conversations for hearing impairment
The 2026 arXiv challenge paper defines a machine-learning task for enhancing conversational speech to address hearing impairment. Evolve's review highlights rigorous real-data subjective evaluation, notes that winners were clear on hearing aids but contested on Aria devices, and flags an under-analyzed objective-subjective mismatch. Jon Barker appears in last-author position.
Randomly VAD-masked loss advances multi-speaker extraction on real conversations
This 2026 arXiv study proposes a randomly VAD-masked loss for multi-speaker extraction on real conversational speech, lifting STOI from 0.55 to 0.60. Evolve finds the gains consistent, but notes that absolute quality remains low and that evaluation is speech-only. Jon Barker appears in last-author position.

Timeline

2026OpenAlex records 5 works in the recent three-year window, all dated 2026, with 8 distinct co-authors.
2026CHiME-9 ECHI challenge paper appears on arXiv, defining a machine-learning task for enhancing conversations for hearing impairment (last-author position).
2026Multi-speaker extraction study proposes a randomly VAD-masked loss, reporting STOI improvement from 0.55 to 0.60 on real conversations (last-author position).
2026Topic profile records Speech Recognition and Synthesis (3 works), Emotion and Mood Recognition (2), plus Hearing Loss and Rehabilitation, Speech and Audio Processing, and Domain Adaptation and Few-Shot Learning.

Papers in the Evolve catalog

Frequent co-authors

Robert Sutherland×2 Stefan Goetze×2 Thomas Kuebert×1 Marko Lugger×1 Stefan Petrausch×1 Eline Borch Petersen×1 Juan Azcarreta Ortiz×1 Buye Xu×1

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 OpenAlex only; no ORCID is linked, and 'Jon Barker' is a common name, so this profile is name-resolved from public bibliographic data.
Output and impact axes lack usable data, and the record lists h-index and i10-index as 0, which likely reflects incomplete citation coverage rather than true impact; treat these as unknown.
Counts by year are available for 2026 only, so activity and trend readings rest on a single year.
Qualitative highlights rely on 2 Evolve-reviewed arXiv papers (both 2026, last-author); the reproducibility mean of 55 is computed from these 2 papers.