Dynamic wakewords for speech-enabled devices

A method of modifying the set of one or more wakewords of a speech-enabled device, comprising:

• receiving a spoken utterance;
• parsing the utterance into a natural language request and a speech audio segment, wherein the natural language request instructs the device to accept the speech audio segment as a new wakeword;
• using automatic speech recognition to map the wakeword to a wakeword phonetic sequence;
• building a new wakeword spotter to recognize the new wakeword phonetic sequence as an activation trigger by:
• dividing the new wakeword phonetic sequence into a sequence of two or more successive partial phonetic segments;
• for each partial phonetic segment, providing a corresponding partial wakeword spotter;
• and
• assembling sequentially the provided partial wakeword spotters into a wakeword spotter for the entire new wakeword phonetic sequence.

A method of modifying the set of one or more wakewords of a speech-enabled device, comprising:

• receiving a spoken request;
• parsing the request into a natural language request and a speech audio segment, wherein the natural language request instructs the device to accept the speech audio segment as a new wakeword;
• defining a new wakeword spotter to recognize the new wakeword as an activation trigger by:
• determining additional speech audio samples of the speech audio segment,
• converting the speech audio segment and the additional speech audio samples to phoneme sequences,
• defining the wakeword spotter based on one or more of the phoneme sequences.