Distributed text-to-speech synthesis between a telephone network and a telephone subscriber unit

• US 6,870,914 B1
• Filed: 03/03/2000
• Issued: 03/22/2005
• Est. Priority Date: 01/29/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: SBC Properties, L.P. (AT&T, Inc.)
• Inventors: Hart, Elizabeth Marie, Kaschke, Kevin D., Hardzinski, Mary Louise, McBlain, Thomas Joseph, Bossemeyer, Robert Wesley, Hamrick, Mendel Keith, Multach, Kelly Ann
• Primary Examiner(s): Tsang, Fan
• Assistant Examiner(s): Phan, Joseph T
• Application Number:
  US09/518,790
• Time in Patent Office: 1,845 Days
• Field of Search: 379/88.21, 379/88.19, 379/88.2, 37914204-14208, 379/215.01, 37922108-22111, 379/82, 704258-260
• US Class Current: 379/142.06
• CPC Class Codes: H04M 1/575 Means for retrieving and displaying personal data about calling party
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 2242/22 Automatic class or number identification arrangements
• 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 3/42102 Making use of the called party identifier
• CPC Class Codes: H04M 3/428 Arrangements for placing incoming calls on hold

Abstract

A telecommunications system (600) distributes text-to-speech synthesis (900) between a telephone network (603) and a telephone subscriber unit (602). The telephone network (603) receives (1102) a telephone call from a first telephone subscriber unit (601) over a first communication channel (604) intended for a second telephone subscriber unit (602), determines (1103) that the second telephone subscriber unit (602) subscribes to a speech-based caller identification service provided by the telephone network (603), converts (1107) text information (707), representing the caller identification of the first telephone subscriber unit (601) into symbols (708), encodes (1108) the symbols (708) to form a data stream (709), opens (1109) a second communication channel (605) between the telephone network (603) and the second telephone subscriber unit (602), and sends (1110) the data stream (709) to the second telephone subscriber unit (602) over the second communication channel (605). The second telephone subscriber unit (602) detects (1202) that the telephone network (603) opened the second communication channel (605), receives (1203) the data stream (807) from the telephone network (603), decodes (1206) the data stream (807) to form decoded symbols (808), converts (1207) the decoded symbols (808) to form a speech waveform (809), and generates (1211) speech from the speech waveform (809) to permit a second party associated with the second telephone subscriber unit (602) to listen to the speech to identify an identity of a first party associated with the first telephone subscriber unit (601) prior to accepting the telephone call from the first telephone subscriber unit (601). The symbols (708) may be generated at various points (909, 910) within the distributed text-to-speech synthesizer (900) depending on: the requirements and limitations of the telecommunication system (600).

Claims

1. A method for performing distributed text-to-speech synthesis by a telephone network coupled to a first telephone subscriber unit and a second telephone subscriber unit, the first telephone subscriber unit having a first telephone number and associated with a first party by the telephone network, and the second telephone subscriber unit having a second telephone number and associated with a second party by the telephone network, the method comprising the steps of:

receiving a telephone call from the first telephone subscriber unit to the telephone network over a first communication channel responsive to the first telephone subscriber unit originating the telephone call to the second telephone subscriber unit through the telephone network;

determining that the second party subscribes to a speech-based caller identification service provided by the telephone network responsive to the step of receiving the telephone call;

placing the first telephone subscriber unit on hold responsive to the step of determining;

sending a ringing signal to the first telephone subscriber unit over the first communication channel responsive to the step of placing;

retrieving text information, representing caller identification information of the first party, from a database stored in a network memory device responsive to the step of determining;

converting the text information into symbols comprising phonemic and prosoidic information, representing the caller identification information of the first party, responsive to the step of retrieving;

encoding the symbols to form a data stream representing the caller identification information of the first party;

opening a second communication channel between the telephone network and the second telephone subscriber unit responsive to the step of encoding;

sending the data stream from the telephone network to the second telephone subscriber unit over the second communication channel responsive to the step of opening;

sending a ringing signal to the second telephone subscriber unit over the second communication channel responsive to the step of sending the data stream;

receiving a request from the second telephone subscriber unit over the second communication channel that the telephone network route the telephone call to the second telephone subscriber unit responsive to the step of sending the ringing signal to the second telephone subscriber unit over the second communication channel;

stopping the sending of the ringing signal to the first telephone subscriber unit over the second communication channel responsive to the step of receiving the request;

taking the first telephone subscriber unit off hold responsive to the step of stopping; and

routing the telephone call through the telephone network from the first telephone subscriber unit over the first communication channel to the second telephone subscriber unit over the second communication channel responsive to the step of taking the first telephone subscriber unit off hold.

2. The method according to claim 1 further comprising the steps of:

determining that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful responsive the step of sending the data stream and responsive to a response from the second telephone subscriber unit that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful, wherein the step of sending the ringing signal is responsive to the step of determining that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful.

3. A method for performing distributed text-to-speech synthesis by a telephone network coupled to a first telephone subscriber unit and a second telephone subscriber unfit, the first telephone subscriber unit having a first telephone number and associated with a first party by the telephone network, and the second telephone subscriber unit having a second telephone number and associated with a second party by the telephone network, the method comprising the steps of:

receiving a telephone call from the first telephone subscriber unit to the telephone network over a first communication channel responsive to the first telephone subscriber unit originating the telephone call to the second telephone subscriber unit through the telephone network;

determining that the second party subscribes to a speech-based caller identification service provided by the telephone network responsive to the step of receiving the telephone call;

placing the first telephone subscriber unit on hold responsive to the step of determining;

sending a ringing signal to the first telephone subscriber unit over the first communication channel responsive to the step of placing;

retrieving text information, representing caller identification information of the first party, from a database stored in a network memory device responsive to the step of determining;

converting the text information into symbols comprising spectral and prosodic feature parameters, representing the caller identification information of the first party, responsive to the step of retrieving;

encoding the symbols to form a data stream representing the caller identification information of the first party;

opening a second communication channel between the telephone network and the second telephone subscriber unit responsive to the step of encoding;

sending the data stream from the telephone network to the second telephone subscriber unit over the second communication channel responsive to the step of opening;

sending a ringing signal to the second telephone subscriber unit over the second communication channel responsive to the step of sending the data stream;

receiving a request from the second telephone subscriber unit over the second communication channel that the telephone network route the telephone call to the second telephone subscriber unit responsive to the step of sending the ringing signal to the second telephone subscriber unit over the second communication channel;

stopping the sending of the ringing signal to the first telephone subscriber unit over the second communication channel responsive to the step of receiving the request;

taking the first telephone subscriber unit off hold responsive to the step of stopping; and

routing the telephone call through the telephone network from the first telephone subscriber unit over the first communication channel to the second telephone subscriber unit over the second communication channel responsive to the step of taking the first telephone subscriber unit off hold.

4. The method according to claim 3 further comprising the steps of:

determining that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful responsive the step of sending the data stream and responsive to a response from the second telephone subscriber unit that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful, wherein the step of sending the ringing signal is responsive to the step of determining that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful.

5. A method for performing distributed text-to-speech synthesis by a telephone network coupled to a first telephone subscriber unit and a second telephone subscriber unit, the first telephone subscriber unit having a first telephone number and associated with a first party by the telephone network, and the second telephone subscriber unit having a second telephone number and associated with a second party by the telephone network, the method comprising the steps of:

receiving a telephone call from the first telephone subscriber unit to the telephone network over a first communication channel responsive to the first telephone subscriber unit originating the telephone call to the second telephone subscriber unit through the telephone network;

determining that the second party subscribes to a speech-based caller identification service provided by the telephone network responsive to the step of receiving the telephone call;

placing the first telephone subscriber unit on hold responsive to the step of determining;

sending a ringing signal to the first telephone subscriber unit over the first communication channel responsive to the step of placing;

retrieving text information, representing caller identification information of the first party, from a database stored in a network memory device responsive to the step of determining;

converting the text information from a first data format to a second data format suitable for text-to-speech synthesis prior to the step of converting the text information into symbols;

converting the text information into symbols, representing the caller identification information of the first party, responsive to the step of retrieving;

encoding the symbols to form a data stream representing the caller identification information of the first party;

opening a second communication channel between the telephone network and the second telephone subscriber unit responsive to the step of encoding;

sending the data stream from the telephone network to the second telephone subscriber unit over the second communication channel responsive to the step of opening;

sending a ringing signal to the second telephone subscriber unit over the second communication channel responsive to the step of sending the data stream;

receiving a request from the second telephone subscriber unit over the second communication channel that the telephone network route the telephone call to the second telephone subscriber unit responsive to the step of sending the ringing signal to the second telephone subscriber unit over the second communication channel;

stopping the sending of the ringing signal to the first telephone subscriber unit over the second communication channel responsive to the step of receiving the request;

taking the first telephone subscriber unit off hold responsive to the step of stopping; and

routing the telephone call through the telephone network from the first telephone subscriber unit over the first communication channel to the second telephone subscriber unit over the second communication channel responsive to the step of taking the first telephone subscriber unit off hold.

6. The method according to claim 5 further comprising the steps of:

determining that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful responsive the step of sending the data stream and responsive to a response from the second telephone subscriber unit that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful, wherein the step of sending the ringing signal is responsive to the step of determining that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful.

7. A method for performing distributed text-to-speech synthesis by a telephone network coupled to a first telephone subscriber unit and a second telephone subscriber unit, the first telephone subscriber unit having a first telephone number and associated with a first party by the telephone network, and the second telephone subscriber unit having a second telephone number and associated with a second party by the telephone network, the method comprising the steps of:

receiving a telephone call from the first telephone subscriber unit to the telephone network over a first communication channel responsive to the first telephone subscriber unit originating the telephone call to the second telephone subscriber unit through the telephone network;

determining that the second party subscribes to a speech-based caller identification service provided by the telephone network responsive to the step of receiving the telephone call;

placing the first telephone subscriber unit on hold responsive to the step of determining;

sending a ringing signal to the first telephone subscriber unit over the first communication channel responsive to the step of placing;

retrieving text information, representing caller identification information of the first party, from a database stored in a network memory device responsive to the step of determining;

converting the text information into symbols comprising phonemic and prosodic information, representing the caller identification information of the first party, responsive to the step of retrieving;

encoding the symbols to form a data stream representing the caller identification information of the first party;

opening a second communication channel between the telephone network and the second telephone subscriber unit responsive to the step of encoding;

sending the data stream from the telephone network to the second telephone subscriber unit over the second communication channel responsive to the step of opening;

determining that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful responsive the step of sending the data stream and responsive to a response from the second telephone subscriber unit over the second communication channel that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful;

sending a ringing signal to the second telephone subscriber unit over the second communication channel responsive to the step of determining that the transmission of the data stream over the second communication channel is successful;

receiving a request from the second telephone subscriber unit over the second communication channel that the telephone network route the telephone call to the second telephone subscriber unit over the second communication channel responsive to the step of sending the ringing signal to the second telephone subscriber unit;

stopping the sending of the ringing signal to the first telephone subscriber unit over the first communication channel responsive to the step of receiving the request;

taking the first telephone subscriber unit off hold responsive to the step of stopping; and

routing the telephone call through the telephone network from the first telephone subscriber unit over the first communication channel to the second telephone subscriber unit over the second communication channel responsive to the step of taking the first telephone subscriber unit off hold.

8. A method for performing distributed text-to-speech synthesis by a telephone network coupled to a first telephone subscriber unit and a second telephone subscriber unit, the first telephone subscriber unit having a first telephone number and associated with a first party by the telephone network, and the second telephone subscriber unit having a second telephone number and associated with a second party by the telephone network, the method comprising the steps of:

receiving a telephone call from the first telephone subscriber unit to the telephone network over a first communication channel responsive to the first telephone subscriber unit originating the telephone call to the second telephone subscriber unit through the telephone network;

determining that the second party subscribes to a speech-based caller identification service provided by the telephone network responsive to the step of receiving the telephone call;

placing the first telephone subscriber unit on hold responsive to the step of determining;

sending a ringing signal to the first telephone subscriber unit over the first communication channel responsive to the step of placing;

retrieving text information, representing caller identification information of the first party, from a database stored in a network memory device responsive to the step of determining;

converting the text information into symbols comprising spectral and prosodic feature parameters, representing the caller identification information of the first party, responsive to the step of retrieving;

encoding the symbols to form a data stream representing the caller identification information of the first party;

opening a second communication channel between the telephone network and the second telephone subscriber unit responsive to the step of encoding;

sending the data stream from the telephone network to the second telephone subscriber unit over the second communication channel responsive to the step of opening;

determining that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful responsive the step of sending the data stream and responsive to a response from the second telephone subscriber unit over the second communication channel that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful;

sending a ringing signal to the second telephone subscriber unit over the second communication channel responsive to the step of determining that the transmission of the data stream over the second communication channel is successful;

receiving a request from the second telephone subscriber unit over the second communication channel that the telephone network route the telephone call to the second telephone subscriber unit over the second communication channel responsive to the step of sending the ringing signal to the second telephone subscriber unit;

stopping the sending of the ringing signal to the first telephone subscriber unit over the first communication channel responsive to the step of receiving the request;

taking the first telephone subscriber unit off hold responsive to the step of stopping; and

routing the telephone call through the telephone network from the first telephone subscriber unit over the first communication channel to the second telephone subscriber unit over the second communication channel responsive to the step of taking the first telephone subscriber unit off hold.

9. A method for performing distributed text-to-speech synthesis by a telephone network coupled to a first telephone subscriber unit and a second telephone subscriber unit, the first telephone subscriber unit having a first telephone number and associated with a first party by the telephone network, and the second telephone subscriber unit having a second telephone number and associated with a second party by the telephone network, the method comprising the steps of:

receiving a telephone call from the first telephone subscriber unit to the telephone network over a first communication channel responsive to the first telephone subscriber unit originating the telephone call to the second telephone subscriber unit through the telephone network;

determining that the second party subscribes to a speech-based caller identification service provided by the telephone network responsive to the step of receiving the telephone call;

placing the first telephone subscriber unit on hold responsive to the step of determining;

sending a ringing signal to the first telephone subscriber unit over the first communication channel responsive to the step of placing;

retrieving text information, representing caller identification information of the first party, from a database stored in a network memory device responsive to the step of determining;

converting the text information from a first data format to a second data format suitable for text-to-speech synthesis prior to the step of converting the text information into symbols;

converting the text information into symbols, representing the caller identification information of the first party, responsive to the step of retrieving;

encoding the symbols to form a data stream representing the caller identification information of the first party;

opening a second communication channel between the telephone network and the second telephone subscriber unit responsive to the step of encoding;

sending the data stream from the telephone network to the second telephone subscriber unit over the second communication channel responsive to the step of opening;

determining that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful responsive the step of sending the data stream and responsive to a response from the second telephone subscriber unit over the second communication channel that the transmission of the data stream from the telephone network to the second telephone subscriber unit over the second communication channel is successful;

sending a ringing signal to the second telephone subscriber unit over the second communication channel responsive to the step of determining that the transmission of the data stream over the second communication channel is successful;

receiving a request from the second telephone subscriber unit over the second communication channel that the telephone network route the telephone call to the second telephone subscriber unit over the second communication channel responsive to the step of sending the ringing signal to the second telephone subscriber unit;

stopping the sending of the ringing signal to the first telephone subscriber unit over the first communication channel responsive to the step of receiving the request;

taking the first telephone subscriber unit off hold responsive to the step of stopping; and

routing the telephone call through the telephone network from the first telephone subscriber unit over the first communication channel to the second telephone subscriber unit over the second communication channel responsive to the step of taking the first telephone subscriber unit off hold.