LipConfirm
Alone, a whisper can be ambiguous. Combined with your typing, it can help distinguish “live” from “love” or recover a garbled word. Typing stays primary. Fix a word with a brief cue instead of backspacing, while keeping most of your message unspoken.
All 30 claims allowed · U.S. Patent No. 12,737,540 scheduled to issue September 15, 2026.
restaurant
Generate candidates from typing first, then use lip or whisper evidence to rescore and select.
Typing only · no auxiliary evidence
Type the word to see its candidates.
Waiting for the mistyped word.
Illustrative simulation. No microphone or camera is accessed.
Typing stays primary in this simulation. Whisper and lip cues guide correction rather than provide a standalone dictation or lipreading result. A single articulation can supply both cues in a combined implementation; combined capture is not simulated here.
Even LLM-informed autocorrect can struggle with garbled input or a typo that produces another valid word, such as a slip from “love” to “live” or “this” to “thus”. A quiet cue together with your typing adds evidence of what you intended, beyond what spelling and context alone can establish.
A faint whisper combined with your typing can be more useful than the same ambiguous whisper alone. Partial clues, such as syllable rhythm or a distinguishing vowel, can help infer the intended word when evaluated together with your typing. LipConfirm uses that evidence without requiring a reliable standalone transcript. Whisper assistance needs no camera.
Silently mouth a word and let a brief, requested camera capture add visual evidence. LipConfirm can use visemes, visible lip shapes associated with speech sounds, and the transitions between them to help resolve your typing. The camera need only run for that brief capture, rather than throughout typing.
Quietly articulate a word as you type it, or add a cue after you notice an error. LipConfirm can reconsider that word using the original typing. Optional silent lip assistance can use a brief, requested camera capture.
When you type for privacy or to avoid disturbing others, even an occasional correction needs to stay quiet. LipConfirm uses the typed letters to help interpret a faint whisper that may be too uncertain to identify the word on its own with standard voice dictation.
A very faint whisper may fail to register or may produce the wrong words at normal typing distance. Speaking louder or moving the phone toward your mouth can help. But raising your voice can quickly approach regular speaking volume, defeating the purpose of staying quiet. Moving the phone closer can also interrupt typing.
LipConfirm is showing that combining faint whisper cues with typed input can make it easier to recover the intended word, even when the typing is garbled.
The point at which dictation becomes unreliable varies by device and setting.
LipConfirm combines that uncertain signal with your typing to help resolve the intended word. The whisper need not be clear enough to identify the word on its own. For a silent alternative, LipConfirm can use your lip movements through a brief, requested camera capture.
Potential accessibility applications. LipConfirm may also make correction easier for people who can type but find repeated backspacing or precise cursor placement difficult. For users who can articulate words but have difficulty producing audible speech, silent lip movements could provide another way to clarify an intended word. The choice of cue can be matched to the user’s abilities and preferences.
Typing errors can leave a word garbled or turn it into another valid word. A brief whisper or silent lip movement can add evidence to help recover what you intended. See what the cue contributes in selected examples below.
U I O sit side by side on a QWERTY keyboard. That makes pairs such as love/live, this/thus, if/of, and pick/puck easy to mistype. These tiny slips can be frustrating because a real word may pass a spelling check, and context does not always rescue the mistake. Faster or less precise typing can also leave a word garbled, making the intended spelling harder to recover from the typed letters alone.
| # | You meant | Typed by mistake |
|---|---|---|
| 01 | love | live |
| 02 | this | thus |
| 03 | if | of |
| 04 | shirt | short |
| 05 | pick | puck |
| 06 | restaurant | restrant |
| 07 | avocado | abcado |
| 08 | appointment | apointmrnt |
| 09 | prescription | prescriotn |
| 10 | accommodation | acxomodatn |
| # | You meant | Typed by mistake |
|---|---|---|
| 11 | I love my life here. | I live my life here. |
| 12 | I left it in the car. | I left it on the car. |
| 13 | I like the shirt dress. | I like the short dress. |
| 14 | We discussed the renovation. | We discussed the renovstn. |
| 15 | Please bring the coat. | Please bring the boat. |
| 16 | The team is ready. | The tea is ready. |
| 17 | Please send the confirmation. | Please send the confrmatn. |
| 18 | I’ll go with the latte. | I’ll go with the latter. |
| 19 | It’s a casual relationship. | It’s a causal relationship. |
| 20 | What about Wednesday? | What about wrfnesdy? |
In the valid-word examples, both versions are grammatical but mean different things. A language model can favor one, yet still miss your intent.
A cue need not reveal the whole word to help resolve it. Even faint whispers often carry clues to syllable count, rhythm, critical vowel or consonant sounds (phonemes), and timing. An optional, brief camera capture can add visemes, visible lip shapes associated with speech sounds, such as closure or rounding, and the movements between them. LipConfirm combines the available cues with the typing to help infer the intended word; audio and lip evidence can also reinforce one another.
In “I love my life here,” a faint “uh” vowel cue can favor love over live, pronounced “liv.” The same vowel contrast helps separate thus from this. Within each pair, the consonants and syllable count match. The typing narrows the choice; the vowel adds evidence context may lack.
If you type abcado but whisper avocado, the surviving letters still provide part of the word’s structure. The whisper can add vowel sounds and syllable rhythm that the garbled spelling does not preserve. LipConfirm can evaluate both together, including in a multimodal model that infers the word directly from the combined inputs. The whisper need not identify the word on its own.
If you type “The tea is ready” but articulate team, the lips close for the final “m.” A captured closure timed to that word ending can support team over tea. LipConfirm can weigh that visible cue alongside the shared typed letters; a resting mouth closure alone would not establish the word.
A captured initial “k” sound can favor coat over boat. In the other direction, boat begins with a “b” made by closing and releasing both lips, while “k” is formed farther back in the mouth. A captured lip closure and release at the word’s start can support boat when evaluated together with the typing.
When casual is articulated with three syllables, its rhythm differs from the usual two syllables of causal. The vowel and middle consonant sounds also differ. LipConfirm can weigh those clues against the nearly identical typed letters. Pronunciation varies, so syllable count is supporting evidence rather than a fixed rule.
These words differ by the neighboring “i” and “o” keys. Their vowel visemes can also differ: the “ih” in if can have a different visible shape from the more open vowel in a fully articulated of. LipConfirm can weigh that shape and its transition into the final consonant against the typing, with whisper audio when available. The visible contrast depends on pronunciation and articulation.
These walkthroughs illustrate how cues can support correction. Pronunciation and capture quality determine which evidence is available. When the combined evidence is insufficient, LipConfirm can retain the typed word or offer alternatives.
LipConfirm is designed to bring typed input and supporting whisper or lip evidence into existing keyboard, autocorrect, spell-checking, and language-model infrastructure. Technical demonstrations and IP discussions available. Desktop prototypes cover both whisper-assisted and lip-assisted correction.
Whisper or silently mouth a word as you type it, or after you notice a mistake. LipConfirm captures the whisper through the microphone, or briefly uses the camera to track silent lip movements when you request help. The whisper does not need to produce a reliable dictation transcript, and the camera need not stay on throughout typing.
Rerank candidates: Start with suggestions generated from typing, then use whisper or lip evidence to rescore or extend those candidates.
Infer with a multimodal model: Evaluate typing and whisper or lip evidence together in a learned model to infer the intended word. The word need not already appear in a separate autocorrect list.
The combined evidence can update a suggestion, confirm a word, or correct a valid word that was typed unintentionally. Confidence controls matter for familiar words as well as garbled input: when the evidence is insufficient, the system can retain the text or offer alternatives.
A faint whisper often retains useful clues to syllable count and rhythm, critical vowel or consonant sounds (phonemes), and sound timing. LipConfirm evaluates the available acoustic evidence together with the original typing, including garbled text. The whisper need not identify the word independently: a partial cue can help resolve the intended word when combined with the typing. A desktop demo of whisper-assisted correction is available.
The capture path must preserve that weak signal. Depending on the system, speech-detection gates or audio filtering can exclude faint utterances before they reach recognition. A user-enabled typing session or requested capture can provide a path for evaluating the retained acoustic evidence with the text. A blank dictation result alone does not identify which stage failed.
Phonetic background: research on whispered speech documents vowel resonances and sound durations despite the absence of normal vocal-fold vibration. This helps explain why incomplete acoustic evidence can remain informative; it does not establish a minimum usable volume for LipConfirm.
Whisper remains the primary auxiliary cue. If you prefer not to whisper at all, LipConfirm can briefly use the camera to track your silent lip movements when you request assistance. It is designed to recognize visemes, the transitions between them, and visual syllable patterns such as the rhythm of mouth opening and closing. These provide alternative visual evidence to evaluate alongside the original typing.
The table below shows examples of visemes detected by the current LipConfirm desktop demo.
| Viseme category | Visible pattern and example sounds |
|---|---|
| CLOSED Bilabial | Both lips meet, as for /p/ in pat, /b/ in bat, and /m/ in mat. |
| LABIO | The lower lip contacts the upper teeth, as for /f/ in fan and /v/ in van. |
| SPREAD | The lips spread for an “ee” sound, /iː/, as in see. |
| OPEN | The mouth opens for an “ah” sound, /ɑ/, as in father. |
| ROUNDED | The lips round or protrude for “oo,” /uː/, as in food, or “oh,” /oʊ/, as in go. |
| MID | A relaxed, moderately open mouth shape for “ih,” /ɪ/, as in sit or if. |
LipConfirm can combine these shapes, their transitions, and visual syllable patterns with the typed letters. For example, a final CLOSED shape can support team over tea; a SPREAD or MID vowel shape can help separate words with “ee” or “ih” sounds.
These references provide background for the visual speech cues and articulation described above. LipConfirm’s preliminary correction results are described separately in the accuracy FAQ.
All 30 claims allowed. U.S. Patent No. 12,737,540 is scheduled to issue September 15, 2026. The allowed claim set addresses lip-assisted correction, shared multimodal operation, and a camera-free whisper-assisted pathway that generates textual proxies for an existing spell-correction engine.
Two U.S. continuation applications are pending, seeking additional protection for lip and whisper-assisted autocorrect. One has been granted Track One prioritized examination.
PCT/US2026/035963 is pending. The USPTO, acting as the International Searching Authority, issued a written opinion with positive novelty, inventive-step, and industrial-applicability findings for all 30 claims. The international search report contains no category X or Y citations.
You may prefer typing to keep most of a message unspoken or avoid disturbing others. The whisper you are comfortable making at normal typing distance may also be too faint for reliable dictation. LipConfirm adds the evidence in your actual typed input, so the same uncertain whisper can help resolve a word without having to identify it independently. This can be useful even as dictation improves.
LipConfirm is showing that combining faint whisper cues with typed input can help identify the intended word, including when the typing is garbled. These are early findings from selected desktop demonstrations. A representative accuracy percentage across users, devices, noise levels, and normal phone typing distances has not yet been established. Broader evaluation needs to count both recovered words and unwanted corrections.
No. Familiar words can be mistyped into other valid words, including love/live and this/thus. “I love my life here” and “I live my life here” are both grammatical, so even a strong language model may not settle the user’s intent from context alone. A whisper or lip cue can supply additional evidence; confidence checks determine whether to change the word.
The microphone can capture a faint whisper even when dictation cannot reliably transcribe it. Useful acoustic clues can remain in that audio even if dictation returns no text or the wrong word. LipConfirm uses the captured signal together with your original typing to help infer the intended word, without requiring a reliable standalone transcript. Try the progressively fainter whisper check at your usual typing distance.
A very faint whisper can help protect privacy by making a correction harder to overhear. Whispers vary in volume, and a faint cue can be much less audible nearby than an ordinary whisper. LipConfirm combines the captured signal with your typing, so even a cue too faint for reliable dictation can help clarify the intended word. Most of your message stays unspoken, and optional silent lip assistance provides a silent path.
For data privacy, the architecture supports local processing and discarding raw audio or mouth-region frames. The host platform determines the implemented data handling.
Here, whisper-level audio means quiet acoustic evidence, including faint, low-amplitude or breathy speech. The aim is to use a comfortable brief cue while keeping the phone where you normally type. LipConfirm evaluates that evidence with the typed input; a complete, correct standalone transcript is not required. Usable volume depends on capture settings, microphone distance, background noise, and the model.
No. Whisper-assisted correction combines microphone input with typing and does not need a camera. Optional lip assistance can provide a silent cue or reinforce a quiet utterance.
Continuous camera use is not required. In the on-demand approach, the camera stays off until lip assistance is requested, captures a short clip of the word, then stops. Longer visual sessions remain an optional, user-enabled configuration.
Yes, in an opted-in typing session. The microphone can remain available so an occasional quiet cue accompanies a word as you type it, including a familiar word that is easy to mistype. Alternatively, it can activate only when assistance is requested. There is no requirement to whisper every word.
The architecture supports associating a new cue with the word just typed and reconsidering the correction using the retained typing evidence. Optional lip assistance can use a brief camera capture requested for that word.
Yes. One quiet articulation can supply audio and lip cues. The architecture combines both with typed evidence and adjusts their influence according to reliability. An unavailable or unreliable channel can contribute less or be omitted.
Desktop demonstrations of whisper-assisted and lip-assisted correction are available. The interactive website demo is an illustrative simulation with preset examples and scores; it does not access your microphone or camera or measure live recognition accuracy.
LipConfirm is designed to support on-device correction without sending raw mouth-region frames or audio to the cloud. Raw sensor data can be discarded after feature extraction or scoring. Deployment choices depend on the host platform and model.
The design supports brief camera use and session-based or requested microphone capture. Actual battery use and latency depend on sensor settings, recognition models, and the device.
LipConfirm can rescore or extend suggestions generated from typing, or infer a correction through a learned multimodal model that evaluates the inputs together. A proxy-string pathway can turn speech-related clues into spelling-like inputs for an existing correction engine. The interactive demo illustrates late and early fusion as two distinct strategies.
Text-assisted correction can use partial cues, such as syllable patterns and mouth shapes, rather than independently recognizing every word from lips alone. Useful visual evidence still depends on articulation and capture quality. Optional personalization can adapt scoring to a user.
The architecture supports keyboard-based correction on phones, tablets, desktop systems, wearables, and extended-reality devices. Each platform can use the available, user-permitted combination of typed, acoustic, and visual evidence.
A high-confidence result can be inserted or confirmed automatically. When the evidence is uncertain, the system can offer alternatives, retain the current text, or wait for another cue. The user does not need to see the internal candidate scores or camera feed.
All 30 claims of the U.S. parent application have been allowed, and U.S. Patent No. 12,737,540 is scheduled to issue September 15, 2026. Two U.S. continuation applications and a PCT international application are pending. One continuation has been granted Track One prioritized examination. See Patent & IP for details.
Email: hello@lipconfirm.com
LipConfirm was conceived and developed by Andre Persidsky, a multidisciplinary engineer and inventor with experience building, patenting, and licensing technology. Andre has previously licensed technology to commercial partners including Spotify, and has led hardware/software health-technology projects in collaboration with external research institutions.