Generation of automated message responses
First Claim
1. A computer-implemented method comprising:
- receiving, from a first device, input audio data including a spoken utterance;
performing speech processing on the input audio data;
determining the input audio data comprises a message intended for a second device associated with a user profile;
generating output text data responding to the input audio data, the output text data being based on the input audio data being received from the first device;
identifying a plurality of stored audio segments associated with the user profile, the stored audio segments comprising speech data previously sent to the first device from the second device;
performing text-to-speech (TTS) processing on the output text data to generate output audio data, wherein the TTS processing uses the plurality of stored audio segments;
determining that the user profile is associated with an unavailable indicator associated with the second device, the unavailable indicator being based on the second device being in operation; and
sending, to the first device in response to determining the user profile is associated with the unavailable indicator, the output audio data.
1 Assignment
0 Petitions
Accused Products
Abstract
Systems, methods, and devices for computer-generating responses and sending responses to communications when the recipient of the communication is unavailable are disclosed. An individual may send a message (either audio or text) to a recipient. The recipient may be unavailable to contemporaneously respond to the message (e.g., the recipient may be performing an action that makes is difficult or impractical for the recipient to contemporaneously respond to the audio message). When the recipient is unavailable, a response to the message is generated and sent without receiving an instruction from the recipient to do so. The response may be sent to the message originating individual, and content of the response may thereafter be sent to the recipient to receive feedback regarding the correctness of the response. Alternatively, the response content may first be sent to the recipient to receive the feedback, and thereafter the response may be sent to the message originating individual.
57 Citations
20 Claims
-
1. A computer-implemented method comprising:
-
receiving, from a first device, input audio data including a spoken utterance; performing speech processing on the input audio data; determining the input audio data comprises a message intended for a second device associated with a user profile; generating output text data responding to the input audio data, the output text data being based on the input audio data being received from the first device; identifying a plurality of stored audio segments associated with the user profile, the stored audio segments comprising speech data previously sent to the first device from the second device; performing text-to-speech (TTS) processing on the output text data to generate output audio data, wherein the TTS processing uses the plurality of stored audio segments; determining that the user profile is associated with an unavailable indicator associated with the second device, the unavailable indicator being based on the second device being in operation; and sending, to the first device in response to determining the user profile is associated with the unavailable indicator, the output audio data. - View Dependent Claims (2, 3, 4)
-
-
5. A system comprising:
-
at least one processor; and at least one memory including instructions that, when executed by the at least one processor, cause the system to; receive, from a first device, input audio data; determine the input audio data represents a message intended for a recipient device associated with a recipient profile; generate text data corresponding to the input audio data; determine the recipient profile is associated with an unavailable indicator; identify, in the recipient profile, a prosodic characteristic associated with voice data previously sent to the first device; perform, using the prosodic characteristic, text-to-speech processing on the text data to generate output audio data; and send, to the first device in response to determining the recipient profile is associated with the unavailable indicator, the output audio data. - View Dependent Claims (6, 7, 8, 9, 10, 11, 12)
-
-
13. A computer-implemented method comprising:
-
receiving, from a first device, input audio data; determine the input audio data represents a message intended for a recipient device associated with a recipient profile; generating text data corresponding to the input audio data; determining the recipient profile is associated with an unavailable indicator; identifying, in the recipient profile, a prosodic characteristic associated with voice data previously sent to the first device; performing, using the prosodic characteristic, text-to-speech processing on the text data to generate output audio data; and sending, to the first device in response to determining the recipient profile is associated with the unavailable indicator, the output audio data. - View Dependent Claims (14, 15, 16, 17, 18, 19, 20)
-
Specification