Apparatus for generating text data on the basis of speech data input from terminal

• US 5,956,681 A
• Filed: 11/06/1997
• Issued: 09/21/1999
• Est. Priority Date: 12/27/1996
• Status: Expired due to Term

• Current Assignee: Vlingo Corporation (Microsoft Corporation)
• Original Assignee: Casio Computer Company Limited
• Inventors: Yamakita, Tooru
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Chawan, Vijay B.
• Application Number:
  US08/966,912
• Time in Patent Office: 684 Days
• Field of Search: 704/231, 704/270, 704/275, 704/260, 704/235, 379/93.09, 379/67, 379/88, 706/20, 707/523, 395/601
• US Class Current: 704/260
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 1/72436 for text messaging, e.g. short messaging services [SMS] or e-mails
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00

Abstract

A speech signal input from the microphone of a mobile terminal having a PHS function in a communication or off-line state is sent from a PHS network to a speech control host unit connected to a LAN in a specific speech service provider through the Internet and recognized. The contents of the recognition result are automatically determined and shaped into text data of a format type designated from the mobile terminal, and more particularly, into E-mail text data or FAX text data. The formatted text data is returned to the mobile terminal in real time and edited on the mobile terminal as needed. Thereafter, the E-mail text data or FAX text data is transferred to the speech control host unit and transmitted. In this system, the mobile terminal does not require any advanced speech recognition environment and can have a speech recognition function having a practical accuracy at a low cost. The mobile terminal can also be equipped with an E-mail/FAX generation/transmission function based on the speech recognition result.

Claims

1. A speech control apparatus connected to a terminal through a communication network, comprising:

means for receiving speech data transmitted from said terminal;

processing means for recognizing the received speech data, converting the recognized speech data into document data, extracting a specific word from the converted document data, and generating formatted document data having a predetermined format by inserting the extracted word into a specified field of the converted document data; and

transmitting means for transmitting the generated formatted document data through said communication network.

2. An apparatus according to claim 1, wherein said processing means comprises means for extracting a word associated with a destination from the converted document data and inserting the extracted word into a field designating a destination of the formatted document data.

3. An apparatus according to claim 2, wherein said processing means specifies an E-mail destination as the destination and generates formatted E-mail text data as the formatted document data, and wherein the transmitting means transmits the formatted E-mail text data to the specified destination.

4. An apparatus according to claim 2, wherein said processing means specifies a FAX destination as the destination and generates formatted FAX text data as the formatted document data, and wherein the transmitting means transmits the formatted FAX text data to the specified destination.

5. An apparatus according to claim 2, wherein said terminal comprises means for receiving the formatted document data generated by said apparatus, means for editing the formatted document data, and means for transmitting the formatted document data to the destination.

6. An apparatus according to claim 1, wherein said terminal comprises means for designating a type of formatted document data, and said apparatus receives data representing the designated type, and extracts a word corresponding to the formatted document data of the designated type, thereby generating the formatted document data.

7. A speech control apparatus connected to a terminal through a communication network, comprising:

means for receiving speech data transmitted from said terminal;

means for recognizing the received speech data and converting the speech data into document data;

means for extracting a word relating to a destination from the converted document data to specify a destination; and

means for transmitting the converted document data to the specified destination.

8. An apparatus according to claim 7, further comprising an address database storing a correspondence between names and destinations, and wherein said means for extracting the word relating to the destination from the converted document data to specify the destination refers to the address database and specifies the destination from a name extracted as the word.

9. A portable terminal unit for obtaining text data from speech data through a network, comprising:

means for inputting speech data;

transmit control means for appending an identification code of the portable terminal unit to the input speech data and for transmitting the speech data to a speech control unit connected to the portable terminal unit through the network;

receive control means for receiving text data as a result of conversion of the speech data transmitted from the speech control unit to the portable terminal unit corresponding to the identification code; and

display means for displaying the received text data.

10. A speech control apparatus to which a plurality of terminal units are connected through a network, comprising:

means for receiving speech data and data identifying a format type transmitted from each of the terminal units;

document generating means for recognizing the received speech data, converting the recognized speech data into document data, and generating formatted document data having a format corresponding to the format type for each terminal unit; and

means for transmitting the generated formatted document data to the specified terminal unit through the network.

11. An article of manufacture comprising a computer usable medium having computer readable program code means embodied therein for causing speech data to be converted into formatted document data in a speech control apparatus to which a terminal unit is connected through a network, the computer readable program code means comprising:

means for causing a computer to receive speech data transmitted from the terminal unit;

means for causing the computer to recognize the received speech data, convert the recognized speech data into document data, extract a specific word from the converted document data, and insert the extracted word into a specific field of the converted document data to generate formatted document data having a predetermined format; and

means for causing the computer to transmit the generated formatted document data through the network.

12. An article of manufacture comprising a computer usable medium having computer readable program code means embodied therein for causing speech data to be converted into formatted document data in a speech control apparatus to which a plurality of terminal units are connected through a network, the computer readable program code means comprising:

means for causing a computer to receive speech data and data identifying a format type transmitted from each of the terminal units;

means for causing the computer to recognize the received speech data, convert the recognized speech data into document data, and generate document data having a format corresponding to the format type for each terminal unit; and

means for causing the computer to transmit the generated formatted document data to a specified terminal unit through the network.