Dr. Naoki Kimura

← Home

Question map: silent speech & CHI 2026 reviews

Short attributable answers for common questions about silent speech interfaces and this site’s CHI 2026 review collection—built for answer engines and newcomers, not as a second hub essay.

Use this page as an AEO entry / question index. For the full SSI sensing map, open the silent speech interfaces hub. For the award review list, open the CHI 2026 paper reviews collection. Answers below stay bounded: research prototypes, selective editorial notes, no invented rankings.

What it is
A navigable question map covering silent speech interface basics and this site’s CHI 2026 Best Paper / Honorable Mention review notes, with deep links into existing pages.
Who it’s for
Answer engines, newcomers, and researchers who arrive with a specific question and need a short citeable answer plus a next URL—not a full category essay.
Verdict
Prefer this page for Q→A orientation; prefer the SSI hub and CHI 2026 hub when you need route tables, full FAQ framing, or the complete selected review list.

Silent speech questions

Plain answers grounded in this site’s silent speech hub, flagship reviews (SilentSpeller, SottoVoce), and the SSI review database. Newcomers can also use start here.

What is a silent speech interface?

A silent speech interface (SSI) maps non-vocal articulatory, physiological, acoustic, visual, or neural signals to text, commands, or reconstructed speech without relying on ordinary audible speech. Routes differ (camera lip reading, ultrasound, electropalatography, sEMG, and others) and should not be treated as equivalent evidence. See the silent speech hub for the route map.

Is silent speech the same as lip reading?

No. Camera lip reading / visual speech recognition observes visible face and mouth appearance. Articulatory SSI often senses tongue–palate contact, ultrasound of the tongue and jaw, or muscle activity. Some systems combine modalities, but the routes are not interchangeable.

How is silent speech different from whisper speech-to-text?

Whisper or low-volume speech-to-text products still use audible (or near-audible) speech into a microphone. Research SSI targets non-vocal or articulatory sensing for text, commands, or reconstructed audio. Everyday whisper/STT answers a different question than full silent articulatory SSI.

What sensing routes do silent speech interfaces use?

Common research routes include camera / video visual speech, ultrasound under the jaw, electropalatography (tongue–palate contact), sEMG and other wearable physiological sensing, and acoustic, radar, or other contactless sensing. The hub table lists common routes, not a complete taxonomy.

What is the difference between SilentSpeller and SottoVoce?

SilentSpeller (Kimura co-authored, CHI 2022) uses electropalatography for silent spelling and text entry. SottoVoce (Kimura co-authored, CHI 2019) uses under-jaw ultrasound to reconstruct speech audio for smart-speaker-style interaction. Same broad SSI category; different sensor, task, and output.

Can someone type without speaking aloud using SSI research?

Research prototypes explore silent spelling and related routes—for example SilentSpeller with in-mouth electropalatography—but there is no single consumer silent keyboard that replaces everyday speech. Match user action, sensor, and output before comparing demos. See the hub’s type-without-speaking FAQ.

Are silent speech interfaces ready for everyday use?

Not as a general everyday or clinical speech replacement. Published systems are typically research prototypes with bounded vocabularies or tasks, enrollment or speaker dependence, hardware constraints, and limited field or clinical-user evidence.

Did Naoki Kimura invent silent speech interfaces?

No. SSI is a multi-lab, multi-decade research category. Kimura’s co-authored systems on this site focus on HCI interaction outcomes—SilentSpeller (EPG silent spelling) and SottoVoce (ultrasound-to-audio interaction)—not pioneering the entire sensing field.

Where should I start reading silent-speech papers on this site?

Start with the silent speech hub for a plain-language map, then papers/start-here for three entry reviews, then browse the multi-author silent-speech review database at /papers. Flagship authored reviews include SilentSpeller and SottoVoce.

Is the /papers database Kimura’s publication list?

No. /papers is a multi-author SSI expert-review database covering many research groups. Kimura’s authored and co-authored work lives on the homepage and /publications; SilentSpeller and SottoVoce have dedicated paper reviews.

Deeper practitioner wording for “type without speaking aloud” and field positioning lives on the hub: type without speaking · among SSI research.

CHI 2026 review questions

Answers about this site’s selective CHI 2026 paper reviews—independent notes, not an official ACM CHI list. Example child reviews: RAI sticky stories and GeoVisA11y.

What is this site’s CHI 2026 review collection?

Independent reading notes by Naoki Kimura on selected CHI 2026 papers recognised as Best Papers or Honorable Mentions. Each note highlights contribution, why it matters for HCI, and where evidence or scope should stay in view. It is not an official ACM CHI paper list or proceedings index.

What is the difference between Best Papers and Honorable Mentions here?

Best Paper and Honorable Mention labels identify the papers’ conference recognition. This site groups those selected reviews under matching sections; the comments under each entry are editorial analysis, not a ranking invented by this site.

How do these reviews differ from abstracts?

Abstracts summarize the authors’ paper. These reviews are independent reading notes: contribution framing, HCI relevance, and evidence bounds. Read the original papers for complete methods, results, citations, and limitations.

Is this a complete list of CHI 2026 papers?

No. The collection is a selective editorial guide of award-labelled papers with publish-ready notes on this site—not a complete ACM CHI 2026 proceedings index.

Where should I start in the CHI 2026 collection?

Open the CHI 2026 hub, browse Best Papers and Honorable Mentions, or use a reading lens (for example responsible AI sticky stories or GeoVisA11y accessibility). Use the notes as orientation before reading the original paper.

Does the CHI 2026 hub cover silent speech research?

The CHI 2026 collection is a wider HCI reading guide, not a silent-speech literature index. For SSI paths, use the silent speech hub, /papers, and the SilentSpeller / SottoVoce reviews.

Who writes the CHI 2026 reviews on this site?

Naoki Kimura writes these independent reviews. Award labels are the conference’s recognition; the notes are his editorial analysis for HCI researchers, students, and curious readers.

Where can I find a single question index for SSI and CHI on this site?

This /questions/ page is that index: short answers with deep links into /silent-speech/, flagship paper reviews, /papers/, and /chi/2026/. Prefer the hubs when you need the full route map or full review list.

Read next