Resolving unique personal identifiers during corresponding conversations between a voice bot and a human

A system comprising:

• one or more processors;
• and
• memory storing instructions that, when executed, the one or more processors are operable to:
• obtain a plurality of training instances, each of the plurality of training instances including:
• training instance input, the training instance input including at least one automatic speech recognition (ASR) speech hypothesis for a unique personal identifier, the unique personal identifier including a unique sequence of alphanumeric characters that is personal to a given human, and
• training instance output, the training instance output including a corresponding ground truth output corresponding to the unique personal identifier;
• train a plurality of machine learning (ML) layers of one or more ML models based on the plurality of training instances, wherein in training the plurality of ML layers based on a given training instance, of the plurality of training instances, one or more of the processors are to:
• process, using the plurality of ML layers, the at least one ASR speech hypothesis for the unique personal identifier to generate a corresponding predicted measure for each of the alphanumeric characters included in the at least one ASR speech hypothesis for the unique personal identifier;
• compare the corresponding predicted measure for each of the alphanumeric characters included in the unique personal identifier to a corresponding ground truth measure for each of the alphanumeric characters included in the corresponding ground truth output corresponding to the unique personal identifier to generate one or more losses;
• and
• cause respective weights of one or more of the plurality of ML layers to be updated based on one or more of the losses;
• and
• subsequent to training the plurality of ML layers based on the plurality of training instances:
• cause a voice bot to utilize the plurality of ML layers in processing one or more ASR speech hypotheses, that are generated while the voice bot is conducting corresponding conversations, to determine unique personal identifiers.

A non-transitory computer-readable storage medium storing instructions that, when executed, cause one or more processors to perform operations, the operations comprising:

• obtaining a plurality of training instances, each of the plurality of training instances including:
• training instance input, the training instance input including at least one automatic speech recognition (ASR) speech hypothesis for a unique personal identifier, the unique personal identifier including a unique sequence of alphanumeric characters that is personal to a given human, and
• training instance output, the training instance output including a corresponding ground truth output corresponding to the unique personal identifier;
• training a plurality of machine learning (ML) layers of one or more ML models based on the plurality of training instances, wherein training the plurality of ML layers based on a given training instance, of the plurality of training instances, comprises:
• processing, using the plurality of ML layers, the at least one ASR speech hypothesis for the unique personal identifier to generate a corresponding predicted measure for each of the alphanumeric characters included in the at least one ASR speech hypothesis for the unique personal identifier;
• comparing the corresponding predicted measure for each of the alphanumeric characters included in the unique personal identifier to a corresponding ground truth measure for each of the alphanumeric characters included in the corresponding ground truth output corresponding to the unique personal identifier to generate one or more losses;
• and
• causing respective weights of one or more of the plurality of ML layers to be updated based on one or more of the losses;
• and
• subsequent to training the plurality of ML layers based on the plurality of training instances:
• causing a voice bot to utilize the plurality of ML layers in processing one or more ASR speech hypotheses, that are generated while the voice bot is conducting corresponding conversations, to determine unique personal identifiers.