/Patent Tracker
GooglePatent applicationAI & softwareInterest 7/10

Google patents speech system that knows when you are done talking

Google describes a method for voice assistants to detect when a speaker has finished a sentence without needing to transcribe the words first. The system analyzes sound waves directly to identify natural pauses, allowing it to start generating a response immediately once the speaker stops.

Why it mattersThis could make voice conversations with devices feel more natural by reducing the awkward silence often required for the system to process what was just said.

In the filing’s own words

A method for turn detection in a speech-to-speech model includes receiving, as input to the speech-to-speech (S2S) model, a sequence of acoustic frames corresponding to an utterance. The method further includes, at each of a plurality of output steps, generating, by an audio encoder of the S2S model, a higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames, and determining, by a turn detector of the S2S model, based on the higher order feature representation generated by the audio encoder at the corresponding output step, whether the utterance is at a breakpoint at the corresponding output step. When the turn detector determines that the utterance is at the breakpoint, the method includes synthesizing a sequence of output audio frames output by a speech decoder of the S2S model into a time-domain audio waveform of synthesized speech representing the utterance spoken by the user.

What exactly they claim (claim 1)

1. A computer-implemented method that when executed on data processing hardware causes the data processing hardware to perform operations comprising: receiving, as input to a speech-to-speech (S2S) model, a sequence of acoustic frames corresponding to an utterance spoken by a user in streaming audio captured by a client device associated with the user, wherein the S2S model is configured to convert output acoustic frames corresponding to synthesized speech directly from input acoustic frames without performing any intermediate speech recognition on the input acoustic frames; and at each of a plurality of output steps: generating, by an audio encoder of the S2S model, a higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames; generating, by a turn detector of the S2S model, based on the higher order feature representation generated by the audio encoder at the corresponding output step, a turn output comprising a probability distribution indicative of whether the utterance is at a breakpoint at the corresponding output step, and when the turn detector determines that the utterance is at the breakpoint, synthesizing a sequence of output audio frames output by a speech decoder of the S2S model into a time-domain audio waveform of synthesized speech, each output audio frame in the sequence of output audio frames based on the higher order feature representations generated by the audio encoder until the corresponding output step when the turn detector generates the turn output comprising the probability distribution indicating that the utterance is at the breakpoint.

Facts

Company
Google (Google LLC)
Official title
STREAMING SPEECH-TO-SPEECH MODEL WITH AUTOMATIC SPEAKER TURN DETECTION
Publication number
US20260290315A1
Application number
19697047
Filed
Jun 3, 2026
Published
Sep 24, 2026
Inventors
2
Claims
20

Classified under

G10L 13/047 Physics & computingG10L 15/04 Physics & computingG10L 15/16 Physics & computingG10L 15/30 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.