Communication method, voice transmission apparatus and voice reception apparatus

• US 6,226,361 B1
• Filed: 04/13/1998
• Issued: 05/01/2001
• Est. Priority Date: 04/11/1997
• Status: Expired due to Fees

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Koyama, Akira
• Primary Examiner(s): Tsang, Fan
• Assistant Examiner(s): Hoosain, Allan
• Application Number:
  US09/058,782
• Time in Patent Office: 1,114 Days
• Field of Search: 379/67.1, 379/88.01, 379/88.02, 379/88.07, 379/88.16, 379/88.17, 704/258, 704/260, 704/264, 704/268, 704/270, 704/272, 704/278, 348/14, 348/15, 348/16, 370/356, 370/394, 370/473
• US Class Current: 379/88.07
• CPC Class Codes: G10L 19/0018 Speech coding using phonetic or linguistical decoding of the source; Reconstruction using text-to-speech synthesis
• CPC Class Codes: H04M 1/2535 adapted for voice communication over an Internet Protocol [IP] network Voice over Internet Protocol (VoIP) network equipment and services H04M7/006; implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP] H04L69/16
• CPC Class Codes: Y10S 379/90 Internet, e.g. Internet phone, webphone, internet-based telephony

Abstract

The invention provided a a communication method, a voice transmission apparatus and a voice reception apparatus by which, in communication through a non-guarantee type network, deterioration in voice, unnatural interruption of language, jump of voice and so forth which arise from unstable communication or a load variation can be eliminated to the utmost to allow conversation which can be recognized readily and conversation by natural voice can be achieved. Voice of a talking person is inputted through a voice to electric conversion element such as a microphone to a voice inputting and outputting element, by which the voice signal is converted into a corresponding voice data electric signal. The voice data are inputted to a speech recognition and conversion section, by which they are converted into a character code data signal by speech synthesis.

Claims

1. A communication method for communicating voice of a talking person through a non-guarantee type network, comprising the steps of:

converting, by a call originating side terminal, voice of a talking person into voice data and speech recognizing the voice data to convert the voice data into character data;

connecting the call originating side terminal to a call terminating side terminal through the non-guarantee type network based on identification data of the call terminating side terminal;

transmitting, after the connection between the call originating side terminal and the call terminating side terminal is established, the character data as packets toward the call terminating side terminal; and

receiving the packet character data by the call terminating side terminal, converting the received character data in the form of packets into voice data by speech synthesis and outputting the voice data as voice;

wherein the voice data are speech recognized divisionally for each predetermined number of words to convert the voice data into character data; and

wherein, in parallel to the speech recognition, the voice data are compressed in units of a predetermined number of words to produce compression voice data, and when the speech recognition is insufficient or results in failure, the compression voice data are sent out as packets.

2. A communication method as claimed in claim 1, wherein a voice profile which represents a characteristic of voice inputted to the call originating side terminal is transmitted in advance from the call originating side terminal to the call terminating side terminal, and upon speech synthesis by the call terminating side terminal, the character data are converted into voice data based on the voice profile.

3. A communication method as claimed in claim 1, wherein a speech synthesis standard pattern for standard voice is prepared by both of the call originating side terminal and the call terminating side terminal, and the call originating side terminal produces finite difference data of voice inputted to the call originating side terminal from the standard voice and sends out the finite difference data together with the packet character data whereas the call terminating side terminal synthesizes voice based on the speech synthesis standard pattern and the finite difference data.

4. A communication method as claimed in claim 1, wherein the call originating side terminal sends out background sound source data corresponding to background sound together with the packet character data whereas the call terminating side terminal outputs the voice data and background sound in a superposed relationship with each other.

5. A communication method as claimed in claim 1, wherein sample voice data are prepared in advance in the call originating side terminal, and when voice of the talking person is inputted first to the call originating side terminal, the voice data and the sample voice data are compared with each other to discriminate whether or not the voice data and the sample voice data originate from the same talking person, and then only when it is discriminated that the voice data and the sample voice data originate from the same talking person, transmission is permitted.

6. A communication method as claimed in claim 1, wherein the call originating side terminal produces image data obtained by imaging the talking person and sends out the image data to the call terminating side terminal, and the call terminating side terminal displays an image based on the received image data.

7. A communication method as claimed in claim 1, wherein the call terminating side terminal displays the received packet character data in the form of characters.

8. A communication method as claimed in claim 1, wherein the call terminating side terminal converts the received packet character data into an electronic mail.

9. A communication apparatus, comprising:

a voice transmission apparatus, comprising;

voice inputting means for converting for converting voice of a talking person into voice data;

speech recognition means for speech recognizing the voice data to convert the voice data into character data;

identification data inputting means for inputting identification data for identification of a particular communication object party on a non-guarantee type network;

network connection means for connecting said voice transmission apparatus to the particular communication object party based on the identification data through said non-guarantee type network; and

transmission means for sending out the character data as packets to said non-guarantee type network;

wherein, upon successful recognition of the voice for converting the voice into character data, said speech recognition means converts the character data into packets, but upon unsuccessful recognition, said speech recognition means compresses the voice data and converts the compressed voice data into packets.

10. The communication apparatus of claim 9, further comprising:

a voice reception apparatus, comprising;

network connection means for connecting said voice reception apparatus to a non-guarantee type network based on an identification signal which specifies said voice reception apparatus;

reception means for receiving character data in the form of packets from said non-guarantee type network;

speech synthesis conversion means for converting the received packet character data into voice data by speech synthesis; and

voice outputting means for outputting voice based on the voice data obtained by the conversion.