Systems and methods for dynamically adjusting a listening time of a voice assistant device

A system for dynamically adjusting a predefined listening time of a voice assistant device, the system comprising:

• a receiving module configured to receive an audio input;
• a breath analysis module configured to analyze the audio input;
• a listening time adjustment module configured to adjust the predefined listening time of the voice assistant device;
• a memory storing at least one instruction;
• and
• at least one processor configured to execute the at least one instruction to:
• receive, via the receiving module, the audio input;
• extract, via the breath analysis module, at least one of a speech component and a non-speech artifact from the audio input;
• determine, via the breath analysis module, a breathing pattern of a user based on (i) 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;
• identify, via the breath analysis module, 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;
• determine, via the listening time adjustment module, 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 adjust the predefined listening time of the voice assistant device, via the listening time adjustment module, to continue listening for voice commands in the conversation based on the intention is to continue the conversation.

A non-transitory computer readable medium for storing computer readable program code or instructions which are executable by one or more processors to perform a method of dynamically adjusting a predefined listening time of a voice assistant device, the method comprising:

• receiving 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 impact 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.