Translation Glasses That Separate the Wearer's Voice From Other Speakers

Post By: By: NeoKnox

In a two-person exchange, the wearer needs to follow the other speaker while also taking a turn to reply. Separating those voices for live captions is a different task from recording and labeling everyone in a meeting.

RayNeo iO distinguishes the wearer's voice from other speakers in Live Captions, prioritizing the other person's speech and filtering the wearer's own words from the caption view. This keeps the display focused on the reply that needs understanding during a face-to-face conversation.

Voice Memo offers separate tools for recording: pickup modes for surrounding voices or a speaker directly ahead, plus speaker labels for reviewing the transcript.

Real RayNeo iO microphone opening and white activity indicator

A caption view centered on the other person

In a conversation, the wearer already knows what they intended to say. Repeating those same words across the lens would compete with the answer. The Live Captions behavior on RayNeo iO is designed around that asymmetry: the display prioritizes the speech coming back.

The glasses use a four-microphone array and a bone-conduction sensor as audio inputs, supporting voice distinction in the conversation workflow.

For a bilingual exchange, the two directions each have their own view. The other person's translated speech appears on the glasses, while the wearer's translated reply appears on the phone for the partner to read.

Three kinds of “speaker separation”

The phrase can refer to several behaviors that are easy to mix together. A useful product choice starts with the output needed: a readable reply, a focused recording, or a navigable transcript.

Need Relevant iO feature What the feature does
Follow the person talking to the wearer Live Captions Prioritizes the other person's speech and filters the wearer's voice from the caption view
Record a one-to-one exchange with focused pickup Voice Memo: Voice Isolation Emphasizes the voice directly ahead while reducing background noise
Record a group discussion Voice Memo: Wide Spectrum Captures surrounding voices more evenly
Organize a meeting transcript by speaker Voice Memo with Speaker Recognition enabled Separates speakers in the transcription workflow and supports renaming them

Voice Isolation and Wide Spectrum belong to Voice Memo. Live Captions uses its own voice-prioritization behavior rather than these recording-mode controls.

Live Captions also saves bilingual text with speaker labels after translation, a record kept apart from Voice Memo transcripts. The labels make it easy to follow who said what, turn by turn.

The microphone hardware behind voice separation

A microphone array provides multiple audio inputs. iO combines that array with a bone-conduction input, giving its voice features information beyond a single airborne microphone signal.

The iO microphone array explanation provides additional context for the hardware.

Setting up Live Captions for a face-to-face exchange

Live Captions can be opened from the glasses' App List or the RayNeo AI app for iPhone or Android. For bilingual communication, Translation is enabled in its settings and the two speakers' languages are selected. Wearer-voice filtering belongs to online Live Captions with the glasses' microphones. The RayNeo iO setup guide walks through installation and pairing.

With that setup, the wearer follows the incoming translation on the lens and the partner reads the reply on the phone, or hears it through optional phone voice playback.

Choose the recording mode by the meeting shape

For a conversation that needs a recording and summary rather than immediate translated captions, Voice Memo provides its own choices. Wide Spectrum is the default pickup mode and is intended for meetings, lectures, and multi-person conversations.

Voice Isolation focuses on the voice directly in front of the wearer and reduces background noise. It fits interviews and one-to-one discussions.

The Smart Crown can mark an important moment during Voice Memo recording with a single click.

Close-up of the RayNeo iO Smart Crown and hinge

Questions about separating voices

Where does my translated reply appear if my voice is filtered?

Filtering applies only to the caption view on the lenses. In the face-to-face translation workflow, the wearer's translated speech appears on the phone for the partner.

What is the best Voice Memo mode for a meeting around a table?

Wide Spectrum captures surrounding voices more evenly, which makes it the Voice Memo choice for multi-person discussions.

What is Voice Isolation designed for?

Voice Isolation is a Voice Memo recording mode that focuses on a speaker directly ahead, such as an interview partner. Live Captions has its own behavior for prioritizing the other speaker.

The meeting goal guides the feature choice. For an incoming translated reply, iO's Live Captions prioritization keeps attention on the other person. For a meeting record, Voice Memo offers a separate set of pickup and transcript tools.

Leave a Comment

We'd love to hear your thoughts. Comments are reviewed before publication.

Select Lens and Purchase