Methods, systems and voice managing servers for voice recognition to perform action

A system for voice recognition to perform an action, the system comprising:

• one or more voice-controlled devices, and
• a voice managing server communicably coupled to the one or more voice-controlled devices, the voice managing server configured to:
• receive a voice command,
• identify a first action intended word from the voice command,
• assign a confidence score to the first action intended word,
• alter the confidence score of the first action intended word in a temporal manner, based on confidence scores of second action intended words following the first action intended word in the voice command,
• identify the action when the confidence scores of the first action intended word and the second action intended words exceed a pre-determined confidence score associated therewith;
• perform the identified action associated with one or more voice-controlled devices;
• and
• alter the confidence score of the second action intended words, wherein altering the confidence score of the first action intended word and the second action intended word comprises altering the one or more probability values of the first action intended word and the second action intended words in the temporal manner, and the altered one or more probability values allow the confidence scores to reach the pre-determined confidence score when each of the first action intended word and the second action intended words belong to one class of the plurality of classes.

A voice managing server for voice recognition to perform an action associated with a voice-controlled device, the voice managing server configured to:

• receive the voice command,
• identify a first action intended word from the voice command,
• assign a confidence score to the first action intended word,
• alter the confidence score of the first action intended word in a temporal manner, based on confidence scores of second action intended words following the first action intended word in the voice command,
• identify the action when the confidence scores of the first action intended word and the second action intended words exceed a pre-determined confidence score associated therewith,
• perform the identified action by the voice-controlled device;
• and
• alter the confidence score of the second action intended words, wherein altering the confidence score of the first action intended word and the second action intended word comprises altering the one or more probability values of the first action intended word and the second action intended words in the temporal manner, and the altered one or more probability values allow the confidence scores to reach the pre-determined confidence score when each of the first action intended word and the second action intended words belong to one class of the plurality of classes.