Voice user interface for wired communications system

• US 10,194,023 B1
• Filed: 08/31/2017
• Issued: 01/29/2019
• Est. Priority Date: 08/31/2017
• Status: Expired due to Fees

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Kong, Cheuk-man, Do, Tu Dien, John Chuan, Mee Tchin Jane, Ismail, Usman
• Primary Examiner(s): Tieu, Binh Kien
• Application Number:
  US15/692,444
• Time in Patent Office: 516 Days
• Field of Search: 37914201, 37914204, 37914205, 37914206, 37914209, 3791421, 37914216, 37914217, 379 8803, 379 8821, 379 9305, 379 9307, 379 9323
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: H04M 1/573 Line monitoring circuits for detecting caller identification
• CPC Class Codes: H04M 1/663 Preventing unauthorised calls to a telephone set
• CPC Class Codes: H04M 2201/39 using speech synthesis
• CPC Class Codes: H04M 2203/2072 Schedules, e.g. personal calendars
• CPC Class Codes: H04M 2203/354 Reverse directory service
• CPC Class Codes: H04M 3/42042 Notifying the called party of information on the calling party details within substation equipment H04M1/57, signalling details H04Q3/72
• CPC Class Codes: H04M 3/436 Arrangements for screening incoming calls , i.e. evaluating the characteristics of a call before deciding whether to answer it based on the calling party profile H04M3/42059; based on location H04M3/42348; based on presence H04M3/42365; diversion H04M3/54
• CPC Class Codes: H04M 7/0069 comprising a residential gateway, e.g. those which provide an adapter for POTS or ISDN terminals

Abstract

A system capable of connecting a device to a Public Switched Telephone Network (PSTN) using an adapter. The adapter may receive caller identification from the PSTN during a second ringing signal and may send notifications to remote server(s) indicating the caller identification. The remote server(s) may use the caller identification to enable additional functionality in a speech processing system. For example, the remote server(s) may identify contact information corresponding to the caller identification, may determine information about the contact, such as recent meetings, communications, or the like, and may output the information when announcing the incoming call. In addition, the remote server(s) may compare the caller identification to a database of spam and indicate that the incoming call is possible spam.

Claims

1. A computer-implemented method comprising:

receiving, via a data network and from an adapter connected to a public switched telephone network (PSTN) via at least one port, a first notification indicating an incoming telephone call from the PSTN, the first notification corresponding to a first ringing signal received by the adapter from the PSTN;

generating first text data that indicates the incoming telephone call;

generating, using text-to-speech processing, first audio data using the first text data;

receiving, via the data network and from the adapter, a second notification corresponding to the incoming telephone call, the second notification corresponding to a second ringing signal received by the adapter from the PSTN, the second notification including caller identification associated with the incoming telephone call that is received from the PSTN, the caller identification indicating at least one of a phone number or a name;

determining contact information associated with the caller identification, the contact information associated with at least one of the phone number or the name;

generating second text data corresponding to the contact information;

generating, using text-to-speech processing, second audio data using the second text data;

generating combined audio data by combining the first audio data and the second audio data; and

sending, to a device via the data network, the combined audio data.

2. The computer-implemented method of claim 1, further comprising:

determining a most recent communication associated with the contact information;

determining a most recent calendar meeting associated with the contact information;

determining an upcoming calendar meeting associated with the contact information;

determining third text data indicating at least one of the most recent communication, the most recent calendar meeting, or the upcoming calendar meeting;

generating, using text-to-speech processing, third audio data using the third text data; and

generating the combined audio data by combining the first audio data, the second audio data and the third audio data.

3. The computer-implemented method of claim 1, further comprising:

determining that the phone number is included in a database of phone numbers, the database of phone numbers including phone numbers corresponding to at least one of telemarketers, blocked numbers or international calls;

generating, because the phone number is included in the database of phone numbers, third text data indicating that the incoming telephone call is potentially unwanted;

generating, using text-to-speech processing, third audio data using the third text data; and

generating the combined audio data by combining the first audio data, the second audio data and the third audio data.

4. The computer-implemented method of claim 1, further comprising:

storing the contact information as session data associated with the incoming telephone call;

receiving, from the device via the data network, a command to accept the incoming telephone call;

sending, to the adapter via the data network, an instruction to accept the incoming telephone call and send audio data corresponding to the incoming telephone call to the device, wherein the adapter is configured to facilitate communications from the PSTN to the device;

receiving, from a second device via the data network, a query requesting information about the incoming telephone call;

generating, using the session data, third text data indicating the requested information;

generating, using text-to-speech processing, third audio data using the third text data; and

sending, to the second device via the data network, the third audio data.

5. A computer-implemented method comprising:

receiving, via a data network and from a first device connected to a public switched telephone network (PSTN), a first message corresponding to an incoming telephone call from the PSTN, the first message including first caller information associated with the incoming telephone call;

determining second caller information associated with the first caller information, the second caller information having been absent from the first message;

generating first text data indicating the incoming telephone call, the first text data including the second caller information;

generating, using text-to-speech processing, first audio data based on the first text data; and

sending, to a second device via the data network, the first audio data so as to cause the second device to output audio indicating the incoming telephone call.

6. The computer-implemented method of claim 5, further comprising:

before receiving the first message, receiving, via the data network and from the first device, a second message corresponding to the incoming telephone call; and

after receiving the second message and before receiving the first message;

determining a current application being executed by the second device,

determining dialog data corresponding to a current state associated with the current application, and

storing the dialog data.

7. The computer-implemented method of claim 5, further comprising:

generating display data based on the second caller information, the display data indicating the incoming telephone call and at least a portion of the second caller information;

and

sending, to the second device via the data network, an instruction to display the display data.

8. The computer-implemented method of claim 5, further comprising:

determining context data indicating at least one of a most recent communication, most recent calendar meeting, or upcoming calendar meeting associated with the second caller information; and

generating the first text data based at least in part on the context data.

9. The computer-implemented method of claim 5, further comprising:

determining context data indicating at least one of a most recent communication, most recent calendar meeting, or upcoming calendar meeting associated with the second caller information;

generating display data based at least in part on the context data;

and

sending, to the second device via the data network, an instruction to display the display data.

10. The computer-implemented method of claim 5, further comprising:

determining a phone number corresponding to the first caller information;

determining that the phone number is included in a database of phone numbers, the database of phone numbers including phone numbers corresponding to at least one of telemarketers, blocked numbers or international calls;

generating, based at least in part on the phone number being included in the database of phone numbers, a least a portion of the first text data.

11. The computer-implemented method of claim 5, wherein:

the first caller information corresponds to caller identification received by the first device from the PSTN.

12. The computer-implemented method of claim 5, wherein:

the first caller information corresponds to caller identification received by the first device from the PSTN, the caller identification including at least one of a phone number or a name; and

the second caller information corresponds to contact information associated with at least one of the phone number and the name, the contact information associated with a user profile.

13. The computer-implemented method of claim 5, further comprising:

before receiving the first message, receiving, via the data network and from the first device, a second message corresponding to the incoming telephone call;

determining a device identifier included in the second message, the device identifier associated with the first device;

determining a user profile associated with the device identifier; and

determining at least a portion of the second caller information based on the user profile, the portion of the second caller information corresponding to contact information associated with the user profile.

14. The computer-implemented method of claim 5, further comprising:

before receiving the first message, receiving, via the data network and from the first device, a second message corresponding to the incoming telephone call;

after receiving the second message and before receiving the first message, generating a first portion of the first text data; and

after receiving the first message, generating a second portion of the first text data, the second portion including the second caller information.

15. The computer-implemented method of claim 5, further comprising:

receiving, from the second device via the data network, a command to accept the incoming telephone call; and

sending, to the first device via the data network, an instruction to accept the incoming telephone call and send second audio data corresponding to the incoming telephone call to the second device, wherein the first device is configured to facilitate communications from the PSTN to the second device.

16. The computer-implemented method of claim 14, further comprising:

initiating, after receiving the second first message and before receiving the first message, text-to-speech processing on the first portion of the first text data.

17. A computer-implemented method, comprising:

receiving, via a data network and from a first device connected to a public switched telephone network (PSTN), a first message corresponding to an incoming telephone call from the PSTN, the first message including first caller information associated with the incoming telephone call;

determining second caller information associated with the first caller information, the second caller information having been absent from the first message;

sending, to a second device via the data network, a second message so as to cause the second device to output a user-perceptible indication of the incoming telephone call, the user-perceptible indication including the second caller information;

receiving, from the second device via the data network, a command to accept the incoming telephone call; and

sending, to the first device via the data network, an instruction to accept the incoming telephone call and send first audio data corresponding to the incoming telephone call to the second device, wherein the first device is configured to facilitate communications from the PSTN to the second device.

18. The computer-implemented method of claim 17, further comprising:

storing at least a portion of the first caller information and the second caller information as session data;

receiving, during the incoming telephone call, from a third device via the data network, a query requesting information about the incoming telephone call;

generating, based on the session data, text data indicating the requested information;

generating, using text-to-speech processing, second audio data based on the text data; and

sending, to the third device via the data network, the second audio data.

19. 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, via a data network and from a first device connected to a public switched telephone network (PSTN), a first message corresponding to an incoming telephone call from the PSTN, the first message including first caller information associated with the incoming telephone call;

determine second caller information associated with the first caller information, the second caller information having been absent from the first message;

generate first text data indicating the incoming telephone call, the first text data including at least a portion of the second caller information;

generate, using text-to-speech processing, first audio data based on the first text data; and

send, to a second device via the data network, the first audio data so as to cause the second device to output audio indicating the incoming telephone call.

20. The system of claim 19, further comprising additional instructions that, when executed by the at least one processor, further cause the system to:

generate display data based on the second caller information, the display data indicating the incoming telephone call and at least a portion of the second caller information;

and

send, to the second device via the data network, an instruction to display the display data.

21. The system of claim 19, further comprising additional instructions that, when executed by the at least one processor, further cause the system to:

determine context data indicating at least one of a most recent communication, most recent calendar meeting, or upcoming calendar meeting associated with the second caller information information; and

generate the first text data based at least in part on the context data.