| CPC G10L 25/78 (2013.01) [G10L 15/22 (2013.01); G10L 25/93 (2013.01); G10L 2015/227 (2013.01); G10L 2025/786 (2013.01)] | 20 Claims |

|
1. A method of dynamically adjusting a predefined listening time of a voice assistant device, the method comprising:
receiving, by the voice assistant device, an audio input;
extracting at least one of a speech component and a non-speech artifact from the audio input;
determining a breathing pattern of a user based on (i) the at least one of the speech component and the non-speech artifact and (ii) an input speech feature vector corresponding to the audio input, wherein the breathing pattern of the user is output as a breath vector for further processing and the determining the breathing pattern employs speech feature vector-to-signal regression;
identifying at least one attribute that impacts the breathing pattern based on at least one non-speech component, captured from an environment and the voice assistant device;
determining, after detecting a pause in the audio input, whether an intention of the user is to continue a conversation based on an analysis of the breathing pattern and the at least one attribute; and
dynamically adjusting the predefined listening time of the voice assistant device to continue listening for voice commands in the conversation based on a determination that the intention is to continue the conversation.
|