Automated call requests with status updates
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, relating to synthetic call status updates. In some implementations, a method includes determining, by a task manager module, that a triggering event has occurred to provide a current status of a user call request. The method may then determine, by the task manager module, the current status of the user call request. A representation of the current status of the user call request is generated. Then, the generated representation of the current status of the user call request is provided to the user.
1. A computer-implemented method comprising:
receiving, by call initiation system for placing telephone calls and conducting conversations between a bot of the call initiating system and human representatives of organizations during the telephone calls, an utterance of a human representative of an organization during a telephone call, wherein the utterance of the human representative prompts the bot to repeat itself;
generating, by an intent-to-text module of the call initiation system, a textual reply (i) that restates a previously output reply differently and (ii) according to a predefined workflow that is associated with a task that is being performed for a human user by the call initiation system;
altering the textual reply to the spoken utterance of the human representative of the organization to include a speech disfluency; and
providing, for output by a text-to-speech module of the call initiation system, an audio representation of the altered, textual reply.
2. The method of claim 1 , wherein the speech disfluency comprises a non-lexical utterance.
3. The method of claim 1 , wherein the speech disfluency comprises a filler word.
4. The method of claim 1 , wherein altering the textual reply comprises prepending the speech disfluency to the textual reply.
5. The method of claim 1 , wherein altering the textual reply comprises postpending a spelling of a particular term of the textual reply, to the textual reply.
6. The method of claim 1 , wherein:
the utterance of the human representative of the organization comprises an incomplete utterance, and
altering the textual reply to include the speech disfluency comprises introducing a status check prompt to the textual reply.
7. A call initiating system for placing telephone calls and conducting conversations between a bot and human representatives of organizations during the telephone calls, the system comprising:
a processor configured to execute computer program instructions; and
a computer storage medium encoded with the computer program instructions that, when executed by the processor, cause the system to perform operations comprising:
receiving, by the call initiation system, an utterance of a human representative of an organization during a telephone call, wherein the utterance of the human representative prompts the bot to repeat itself;
generating, by an intent-to-text module of the call initiation system, a textual reply (i) that restates a previously output reply differently and (ii) according to a predefined workflow that is associated with a task that is being performed for a human user by the call initiation system;
altering the textual reply to the spoken utterance of the human representative of the organization to include a speech disfluency; and
providing, for output by a text-to-speech module of the call initiation system, an audio representation of the altered, textual reply.
8. The system of claim 7 , wherein the speech disfluency comprises a non-lexical utterance.
9. The system of claim 7 , wherein the speech disfluency comprises a filler word.
10. The system of claim 7 , wherein altering the textual reply comprises prepending the speech disfluency to the textual reply.
11. The system of claim 7 , wherein altering the textual reply comprises postpending a spelling of a particular term of the textual reply, to the textual reply.
12. The system of claim 7 , wherein:
the utterance of the human representative of the organization comprises an incomplete utterance, and
altering the textual reply to include the speech disfluency comprises introducing a status check prompt to the textual reply.
13. A computer-readable storage device encoded with a computer program, the computer program comprising instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:
receiving, by call initiation system for placing telephone calls and conducting conversations between a bot of the call initiating system and human representatives of organizations during the telephone calls, an utterance of a human representative of an organization during a telephone call, wherein the utterance of the human representative prompts the bot to repeat itself;
generating, by an intent-to-text module of the call initiation system, a textual reply (i) that restates a previously output reply differently and (ii) according to a predefined workflow that is associated with a task that is being performed for a human user by the call initiation system;
altering the textual reply to the spoken utterance of the human representative of the organization to include a speech disfluency; and
providing, for output by a text-to-speech module of the call initiation system, an audio representation of the altered, textual reply.
14. The device of claim 13 , wherein the speech disfluency comprises a non-lexical utterance.
15. The device of claim 13 , wherein the speech disfluency comprises a filler word.
16. The device of claim 13 , wherein altering the textual reply comprises prepending the speech disfluency to the textual reply.
17. The device of claim 13 , wherein altering the textual reply comprises postpending a spelling of a particular term of the textual reply, to the textual reply.