Abstract: An example method includes obtaining first audio data representing one or more initial utterances during an interactive voice session with an interactive voice system (IVS); generating, based on the first audio data, a prediction regarding whether a subsequent utterance of the user in the interactive voice session will contain sensitive information; obtaining second audio data representing the subsequent utterance; determining, based on the prediction, whether to transmit the second audio data to the IVS via a first communication channel; based on a determination not to transmit the second audio data to the IVS via the first communication channel: transmitting third audio data to the IVS via the first communication channel in place of the second audio data; and transmitting the second audio data to a server via a second communication channel that bypasses the IVS.

Abstract: An example method includes obtaining, by a computing system, first audio data representing one or more initial utterances during an interactive voice session with an interactive voice system; generating, by the computing system, based on the first audio data, a prediction regarding whether a subsequent utterance of a user in the interactive voice session will contain sensitive information, wherein the subsequent utterance follows the one or more initial utterances in time; obtaining, by the computing system, second audio data representing the subsequent utterance; determining, by the computing system, based on the prediction and based on a risk profile of the interactive voice system, whether to transmit the second audio data to the interactive voice system; and based on the determination to transmit the second audio data to the interactive voice system, transmitting the second audio data to the interactive voice system.

Abstract: A method comprises obtaining, by a computing system, first audio data representing one or more initial utterances during an interactive voice session with an interactive voice system; generating, by the computing system, based on the first audio data, a prediction regarding whether a subsequent utterance of a user during the interactive voice session will contain sensitive information, the subsequent utterance following the one or more initial utterances in time; obtaining, by the computing system, second audio data representing the subsequent utterance; determining, by the computing system, based on the prediction, whether to transmit the second audio data; and based on a determination not to transmit the second audio data: replacing, by the computing system, the second audio data with third audio data that is based on a voice of the user; and transmitting, by the computing system, the third audio data.

Abstract: An example method includes obtaining first audio data representing one or more initial utterances during an interactive voice session with an interactive voice system (IVS); generating, based on the first audio data, a prediction regarding whether a subsequent utterance of the user in the interactive voice session will contain sensitive information; obtaining second audio data representing the subsequent utterance; determining, based on the prediction, whether to transmit the second audio data to the IVS via a first communication channel; based on a determination not to transmit the second audio data to the IVS via the first communication channel: transmitting third audio data to the IVS via the first communication channel in place of the second audio data; and transmitting the second audio data to a server via a second communication channel that bypasses the IVS.

Abstract: There is a need for more effective and efficient document summarization. This need can be addressed by, for example, techniques for contextual summarization using semantic intelligence. In one example, a method includes identifying a plurality of senses associated with a plurality of words in a document; for each word-sense pair, determining a word-sense probability score; determining, based at least in part on each word-sense probability score for a word-sense pair, one or more context buckets for the document and one or more sense buckets for the document; determining, based at least in part on the one or more context buckets for the document and the one or more sense buckets for the document, the contextual summarization of the document; and performing one or more document processing actions based at least in part on the contextual summarization.

Abstract: An example method includes obtaining, by a computing system, first audio data representing one or more initial utterances during an interactive voice session with an interactive voice system; generating, by the computing system, based on the first audio data, a prediction regarding whether a subsequent utterance of a user in the interactive voice session will contain sensitive information, wherein the subsequent utterance follows the one or more initial utterances in time; obtaining, by the computing system, second audio data representing the subsequent utterance; determining, by the computing system, based on the prediction and based on a risk profile of the interactive voice system, whether to transmit the second audio data to the interactive voice system; and based on the determination to transmit the second audio data to the interactive voice system, transmitting the second audio data to the interactive voice system.

Abstract: An example method comprises obtaining, by a computing system, first audio data representing one or more initial utterances during an interactive voice session with an interactive voice system; generating, by the computing system, based on the first audio data, a prediction regarding whether a subsequent utterance of a user during the interactive voice session will contain sensitive information, the subsequent utterance following the one or more initial utterances in time; obtaining, by the computing system, second audio data representing the subsequent utterance; determining, by the computing system, based on the prediction, whether to transmit the second audio data; and based on a determination not to transmit the second audio data: replacing, by the computing system, the second audio data with third audio data that is based on a voice of the user; and transmitting, by the computing system, the third audio data.

Abstract: There is a need for more effective and efficient document summarization. This need can be addressed by, for example, techniques for contextual summarization using semantic intelligence. In one example, a method includes identifying a plurality of senses associated with a plurality of words in a document; for each word-sense pair, determining a word-sense probability score; determining, based at least in part on each word-sense probability score for a word-sense pair, one or more context buckets for the document and one or more sense buckets for the document; determining, based at least in part on the one or more context buckets for the document and the one or more sense buckets for the document, the contextual summarization of the document; and performing one or more document processing actions based at least in part on the contextual summarization.