Parse prefix-detection in a human-machine interface
AssigneeSoundHound, Inc.
InventorsJennifer Hee Young ZHANG, Patricia Pozon AGUAYO, Jonah PROBELL
Life of this patent
Estimating the term…
Abstract
A speech-based human-machine interface that parses words spoken to detect a complete parse and, responsive to so detecting, computes a hypothesis as to whether the words are a prefix to another complete parse. The duration of no voice activity period to determine an end of a sentence depends on the prefix hypothesis. The user's typical speech speed profile and a short-term measure of speech speed also scale the period. Speech speed is measured by the time between words, and the period scaling uses a continuously adaptive algorithm. The system uses a longer cut-off period after a system wake-up event but before it detects any voice activity.
Claims9
A method of determining a cut-off period for detecting an end of a sentence in a human-machine interface, the method comprising:
- identifying a beginning of a sentence;
- parsing speech from the beginning of the sentence according to a natural language grammar to determine whether the speech received so far constitutes a complete parse;
- and
- applying a model to produce a hypothesis as to whether the speech received so far is a prefix to another complete parse.
A method of continuously adapting a NVAD cut-off period, the method comprising:
- receiving audio of spoken sentences;
- detecting periods of voice activity and no voice activity in the audio;
- maintaining an NVAD cut-off based on the detection;
- responsive to detecting a complete sentence, decreasing the NVAD cut-off period;
- and
- responsive to detecting a period of voice activity within a partial period threshold of detecting a period of no voice activity, increasing the NVAD cut-off period,
- wherein the partial period threshold is less than the NVAD cut-off period.
A method of determining a cut-off period in a human-machine interface, the method comprising:
- detecting a wake-up event;
- waiting for a relatively long initial NVAD cut-off period;
- and
- responsive to detecting voice activity, selecting a shorter NVAD cut-off period.
Dependencies are inferred from the claim text.