| CPC G10L 15/22 (2013.01) [G10L 25/93 (2013.01)] | 17 Claims |
|
1. A device for assisting a respondent in a conversation, the device comprising:
a microphone configured to detect a voice input, wherein the voice input comprises an excerpt from a vocal conversation between a querier and the respondent;
a controller communicatively coupled to the microphone, wherein the controller is configured to:
fetch the voice input from the microphone;
detect a silent period during the vocal conversation between the querier and the respondent, wherein the silent period has a duration;
compare the duration of the silent period with a threshold time period; and
upon detecting that the duration of the silent period is greater than the threshold time period, trigger a transmitter to transmit the voice input to a server; and
the transmitter communicatively coupled to the controller and the server, and configured to transmit the voice input to the server, wherein the server is to:
generate vectors associated with the voice input;
feed the vectors associated with the voice input to a trained Machine Learning (ML) model;
obtain, from the trained ML model, an output corresponding to the vectors, wherein the output comprises at least one token as a response to the conversation; and
a receiver communicatively coupled to the server, and configured to receive from the server, the output generated by the ML model; and
a speaker communicatively coupled with the receiver and configured to:
receive, from the receiver, the output generated by the ML model; and
generate a voice-based response based on the output, for assisting the respondent in responding to the conversation.
|