brianletort.ai
← Library

Google Research Project Relate

Verified evidenceCreator to judge

Personalized speech recognition for transcription, restatement, and text entry

People with non-standard speech need not rely only on listener familiarity, repetition, or text entry.

Customer service · Multi-country Android beta; Ghana user study

An editorial scene for Google Research Project Relate contrasts speak, repeat, gesture, or switch to typing when a listener or device does not understand. with records at least 500 phrases to create a personalized recognition model. in the personalized speech recognition for transcription, restatement, and text entry workflow.

Executive brief

The operating-model shift, in one view.

Assistive AI is not useful merely because it recognizes more speech; onboarding burden, device access, changing voices, and user control determine whether it increases autonomy.

AI value · Feasibility of personalized ASR use in Ghana

Verified

Twenty people with communication difficulties completed a Ghana user study; the study identified feasibility but also access, adaptation, support, and accuracy limitations

The study is a small feasibility evaluation, not proof of universal accuracy or communication benefit; Google currently accepts no new users.

Before

Speak, repeat, gesture, or switch to typing when a listener or device does not understand. → Interpret, ask for clarification, or fail to complete the interaction.

After

Records at least 500 phrases to create a personalized recognition model. → Transcribes speech, restates it in a synthesized voice, or sends text through a keyboard. → Use the output with active listening, gestures, and clarification.

Human boundary

The model proposes a transcript or synthesized restatement; the user decides whether it expresses the intended message.

Why it matters

People with non-standard speech need not rely only on listener familiarity, repetition, or text entry.

How the work changed

Before

How the work ran before the change.

  1. Step 1 of 2

    Person with non-standard speech

    Speak, repeat, gesture, or switch to typing when a listener or device does not understand.

    ControlHuman accommodation

  2. Step 2 of 2

    Listener

    Interpret, ask for clarification, or fail to complete the interaction.

    ControlListener understanding

What changed

People with non-standard speech need not rely only on listener familiarity, repetition, or text entry.

Decision rightHuman moves from creator to judge

After

How the same work runs now.

  1. Step 1 of 3

    User

    Records at least 500 phrases to create a personalized recognition model.

    ControlAndroid, connectivity, and voice stability

  2. Step 2 of 3

    Project Relate

    Transcribes speech, restates it in a synthesized voice, or sends text through a keyboard.

    ControlPersonalized model

  3. Step 3 of 3

    User and listener

    Use the output with active listening, gestures, and clarification.

    ControlHumans retain meaning and communication control

Process model built from the published workflow evidence for Google Research Project Relate. Every step, actor, and control appears in full below.
Every step, actor, and control

Exception path

Users repeat, type, gesture, or ask a listener for clarification when recognition is low; severe or rapidly changing speech can make the model unsuitable.

Work removed

  • Some repeated speech repair
  • Some manual typing for supported users

Decision authority

The model proposes a transcript or synthesized restatement; the user decides whether it expresses the intended message.

Before

  1. 01

    Person with non-standard speech

    Speak, repeat, gesture, or switch to typing when a listener or device does not understand.

    Control: Human accommodation

  2. 02

    Listener

    Interpret, ask for clarification, or fail to complete the interaction.

    Control: Listener understanding

After

  1. 01

    User

    Records at least 500 phrases to create a personalized recognition model.

    Control: Android, connectivity, and voice stability

  2. 02

    Project Relate

    Transcribes speech, restates it in a synthesized voice, or sends text through a keyboard.

    Control: Personalized model

  3. 03

    User and listener

    Use the output with active listening, gestures, and clarification.

    Control: Humans retain meaning and communication control

Work that left the path

  • Some repeated speech repair
  • Some manual typing for supported users

Human role before

Users repeatedly repaired communication and listeners inferred meaning without personalized recognition support.

Human role after

Users train and choose when to use the tool; listeners combine its output with active clarification.

AI rolePersonalized automatic speech recognition trained on an individual's non-standard speech.

Outcomes

Feasibility of personalized ASR use in Ghana

Verified

General ASR can have 78-89% word-error rates for severely dysarthric speech, with 0-1.2% correctly transcribed sentences in cited prior work→Twenty people with communication difficulties completed a Ghana user study; the study identified feasibility but also access, adaptation, support, and accuracy limitations

Study published at CHI 2024 · 20 users plus locally trained speech and language therapists in Ghana

The study is a small feasibility evaluation, not proof of universal accuracy or communication benefit; Google currently accepts no new users.

What leaders can reuse

Anti-pattern

Treating a transcript as the user's intended message or presenting a closed beta as broadly available.

Questions

  1. 01Can the user easily reject or correct the output?
  2. 02What happens as the user's voice changes?

Portability conditions

  • User-specific training data
  • Stable enough speech pattern
  • Fallback communication modes

Reputation risk

high

Evidence and authority

What the public record supports.

Watch · updated

Watch status: verify the cited source and deployment condition before reusing this case.

1 peer reviewed, 2 primary; publication outcomes are verified.

Bundle 1.0.0 · reviewed 2026-08-23 · stable ID 33e321501f83de63

Related transformations

More in Customer service →

Twenty-eight South-East Queensland long-term care facilities · Creator to judge

PARO robotic-seal engagement sessions

Hinge: a responsive social robot can provide repeatable short engagement sessions as an adjunct to care, without replacing clinical assessment or human relationships.

IKEA (Ingka Group) · Creator to judge

Contact-Center Reskilling

Human agents must answer routine queries instead of focusing on high-value sales and design advisory.

Octopus Energy · Creator to judge

AI-Drafted Customer Email / Arlo Assistant

Human agents must draft responses to all customer emails.

Google · Creator to judge

LLM-assisted 32-bit to 64-bit identifier migration

Large migrations can combine machine-found locations, LLM edits, automated checks, and engineer review.

Sources

Read the evidence, freshness, caveat, and version policy.