Speech synthesis system for generating speech information obtained by converting text into speech

A speech synthesis system comprising a server device and a client device connected so as to be capable of communicating with each other, wherein:

• the server device includes:
• a speech element information storing unit configured to store speech element information and speech element identification information in association with each other so that, in a case that speech element information representing respective speech elements included in speech uttered by a speech registering user are arranged in the order of arrangement of the speech elements in the speech, at least one of the speech element identification information identifying the respective speech element information has different information from information arranged in accordance with a predetermined rule;
• a speech-element-identification-information receiving unit configured to receive the speech element identification information from the client device;
• and
• a speech element information transmitting unit configured to transmit the speech element information stored in association with the received speech element identification information to the client device;
• and
• the client device includes:
• a speech-element-identification-information storing unit configured to store speech element specification information specifying a speech element and the speech element identification information in association with each other;
• a text information accepting unit configured to accept text information representing text;
• a speech-element-identification-information transmitting unit configured to generate speech element specification information based on the accepted text information, and transmit speech element identification information stored in association with the generated speech element specification information, to the server device;
• and
• a speech synthesizing unit configured to receive speech element information from the server device and, based on the received speech element information, generate speech information obtained by converting text represented by the accepted text information into speech, wherein the server device includes a communication blocking unit configured to block communication with the client device in a case that the speech element identification information received from the client device is not stored by the speech element information storing unit.

A speech element providing device, comprising:

• a speech element information storing unit configured to store speech element information and speech element identification information in association with each other so that, in a case that speech element information representing respective speech elements included in speech uttered by a speech registering user are arranged in the order of arrangement of the speech elements in the speech, at least one of speech element identification information identifying the respective speech element information has different information from information arranged in accordance with a predetermined rule;
• a speech-element-identification-information receiving unit configured to receive the speech element identification information;
• and
• a speech element information transmitting unit configured to transmit the speech element information stored in a storing device in association with the received speech element identification information, wherein:
• the speech element identification information is information representing an integer;
• and
• the speech element information storing unit is configured to store the speech element information and the speech element identification information in association with each other so that, in a case that integers represented by the speech element identification information corresponding to the speech elements are arranged in the order of arrangement of the speech elements in the speech, the integers include a pair of two adjacent integers in which an integer at the end has a different value from a value obtained by adding 1 to an integer at the beginning.

A speech element providing method, comprising:

• causing a storing device to store speech element information and speech element identification information in association with each other so that, in a case that speech element information representing respective speech elements included in speech uttered by a speech registering user are arranged in the order of arrangement of the speech elements in the speech, at least one of speech element identification information identifying the respective speech element information has different information from information arranged in accordance with a predetermined rule;
• receiving the speech element identification information;
• and
• transmitting the speech element information stored in the storing device in association with the received speech element identification information, wherein the speech element identification information is information representing an integer,
• the speech element providing method comprising, at the time of causing the storing device to store the speech element information and the speech element identification information in association with each other, causing the storing device to store the speech element information and the speech element identification information in association with each other so that, in a case that integers represented by the speech element identification information corresponding to the speech elements are arranged in the order of arrangement of the speech elements in the speech, the integers include a pair of two adjacent integers in which an integer at the end has a different value from a value obtained by adding 1 to an integer at the beginning.

A non-transitory computer-readable medium storing a speech element providing program product comprising computer implementable instructions for causing a speech element providing device comprising a storing device, to realize:

• a speech element-information storing process unit configured to cause the storing device to store speech element information and speech element identification information in association with each other so that, in a case that speech element information representing respective speech elements included in speech uttered by a speech registering user are arranged in the order of arrangement of the speech elements in the speech, at least one of speech element identification information identifying the respective speech element information has different information from information arranged in accordance with a predetermined rule;
• a speech-element-identification-information receiving unit configured to receive the speech element identification information;
• and
• a speech element information transmitting unit configured to transmit the speech element information stored in the storing device in association with the received speech element identification information, wherein:
• the speech element identification information is information representing an integer;
• and
• the speech element-information storing process unit is configured to cause the storing device to store the speech element information and the speech element identification information in association with each other so that, in a case that integers represented by the speech element identification information corresponding to the speech elements are arranged in the order of arrangement of the speech elements in the speech, the integers include a pair of two adjacent integers in which an integer at the end has a different value from a value obtained by adding 1 to an integer at the beginning.

A speech synthesis method applied to a speech synthesis system including a server device and a client device connected so as to be capable of communicating with each other, comprising:

• accepting text information representing text, by the client device;
• generating speech element specification information specifying a speech element, based on the accepted text information, by the client device;
• transmitting, to the server device by the client device, speech element identification information stored in association with the generated speech element specification information in a storing device configured to store speech element identification information identifying speech element information representing a speech element and speech element specification information specifying a speech element in association with each other, the storing device being included by the client device;
• receiving the speech element identification information from the client device, by the server device;
• transmitting, to the client device by the server device, speech element information stored in association with the received speech element identification information in a storing device configured to store speech element information and speech element identification information in association with each other so that, in a case that speech element information representing respective speech elements included in speech uttered by a speech registering user, at least one of the speech element identification information identifying the respective speech element information has different information from information arranged in accordance with a predetermined rule, the storing device being included by the server device;
• and
• receiving the speech element information from the server device and, based on the received speech element information, generate speech information obtained by converting text represented by the accepted text information into speech, by the client device, wherein the speech element identification information is information representing an integer,
• the speech synthesis method comprising, when causing the storing device to store the speech element information and the speech element identification information in association with each other, causing the storing device by the server device, to store the speech element information and the speech element identification information in association with each other so that, in a case that integers represented by the speech element identification information corresponding to the speech elements are arranged in the order of arrangement of the speech elements in the speech, the integers include a pair of two adjacent integers in which an integer at the end has a different value from a value obtained by adding 1 to an integer at the beginning.

A client device connected to a server device so as to be capable of communicating therewith, the client device comprising:

• a speech-element-identification-information storing unit configured to store speech element identification information and speech element specification information in association with each other, the speech element identification information being set so that, in a case that speech element information representing respective speech elements included in speech uttered by a speech registering user are arranged in the order of arrangement of the speech elements in the speech, at least one of speech element identification information identifying the respective speech element information has different information from information arranged in accordance with a predetermined rule, and the speech element specification information specifying a speech element;
• a text information accepting unit configured to accept text information representing text;
• a speech-element-identification-information transmitting unit configured to generate speech element specification information based on the accepted text information and transmit, to the server device, the speech element identification information stored in association with the generated speech element specification information;
• and
• a speech synthesizing unit configured to receive speech element information from the server device and, based on the received speech element information, generate speech information obtained by converting text represented by the accepted text information into speech, wherein the speech element identification information is information representing an integer and is set so that, in a case that integers represented by the speech element identification information corresponding to the speech elements are arranged in the order of arrangement of the speech elements in the speech, the integers include a pair of two adjacent integers in which an integer at the end has a different value from a value obtained by adding 1 to an integer at the beginning.

A non-transitory computer-readable medium storing a speech synthesis program comprising computer implementable instructions for causing a client device connected to a server device so as to be capable of communicating therewith, to realize:

• a text information accepting unit configured to accept text information representing text;
• a speech-element-identification-information transmitting unit configured to generate speech element identification information based on the accepted text information, and transmit, to the server device, the speech element identification information stored in association with the generated speech element specification information in a storing device configured to store speech element identification information and speech element specification information, the speech element identification information being set so that, in a case that speech element information representing respective speech elements included in speech uttered by a speech registering user are arranged in the order of arrangement of the speech elements in the speech, at least one of speech element identification information identifying the respective speech element information has different information from information arranged in accordance with a predetermined rule, and the speech element specification information specifying a speech element;
• and
• a speech synthesizing unit configured to receive speech element information from the server device and, based on the received speech element information, generate speech information obtained by converting text represented by the accepted text information into speech, wherein the speech element identification information is information representing an integer and is set so that, in a case that integers represented by the speech element identification information corresponding to the speech elements are arranged in the order of arrangement of the speech elements in the speech, the integers include a pair of two adjacent integers in which an integer at the end has a different value from a value obtained by adding 1 to an integer at the beginning.

A speech synthesis system comprising a server device and a client device connected so as to be capable of communicating with each other, wherein:

• the server device includes:
• a speech element information storing means configured to store speech element information and speech element identification information in association with each other so that, in a case that speech element information representing respective speech elements included in speech uttered by a speech registering user are arranged in the order of arrangement of the speech elements in the speech, at least one of the speech element identification information identifying the respective speech element information has different information from information arranged in accordance with a predetermined rule;
• a speech-element-identification-information receiving means configured to receive the speech element identification information from the client device;
• and
• a speech element information transmitting means configured to transmit the speech element information stored in association with the received speech element identification information to the client device;
• and
• the client device includes:
• a speech-element-identification-information storing means configured to store speech element specification information specifying a speech element and the speech element identification information in association with each other;
• a text information accepting means configured to accept text information representing text;
• a speech-element-identification-information transmitting means configured to generate speech element specification information based on the accepted text information, and transmit speech element identification information stored in association with the generated speech element specification information, to the server device;
• and
• a speech synthesizing means configured to receive speech element information from the server device and, based on the received speech element information, generate speech information obtained by converting text represented by the accepted text information into speech, wherein:
• the speech element identification information is information representing an integer;
• and
• the speech element information storing unit is configured to store the speech element information and the speech element identification information in association with each other so that, in a case that integers represented by the speech element identification information corresponding to speech elements are arranged in the order of arrangement of the speech elements in the speech, the integers include a pair of two adjacent integers in which an integer at the end has a different value from a value obtained by adding 1 to an integer at the beginning.

A speech element providing device, comprising:

• a speech element information storing means configured to store speech element information and speech element identification information in association with each other so that, in a case that speech element information representing respective speech elements included in speech uttered by a speech registering user are arranged in the order of arrangement of the speech elements in the speech, at least one of speech element identification information identifying the respective speech element information has different information from information arranged in accordance with a predetermined rule;
• a speech-element-identification-information receiving means configured to receive the speech element identification information;
• and
• a speech element information transmitting means configured to transmit the speech element information stored in a storing device in association with the received speech element identification information, wherein:
• the speech element identification information is information representing an integer;
• and
• the speech element information storing unit is configured to store the speech element information and the speech element identification information in association with each other so that, in a case that integers represented by the speech element identification information corresponding to the speech elements are arranged in the order of arrangement of the speech elements in the speech, the integers include a pair of two adjacent integers in which an integer at the end has a different value from a value obtained by adding 1 to an integer at the beginning.

A client device connected to a server device so as to be capable of communicating therewith, the client device comprising:

• a speech-element-identification-information storing means configured to store speech element identification information and speech element specification information in association with each other, the speech element identification information being set so that, in a case that speech element information representing respective speech elements included in speech uttered by a speech registering user are arranged in the order of arrangement of the speech elements in the speech, at least one of speech element identification information identifying the respective speech element information has different information from information arranged in accordance with a predetermined rule, and the speech element specification information specifying a speech element;
• a text information accepting means configured to accept text information representing text;
• a speech-element-identification-information transmitting means configured to generate speech element specification information based on the accepted text information and transmit, to the server device, the speech element identification information stored in association with the generated speech element specification information;
• and
• a speech synthesizing means configured to receive speech element information from the server device and, based on the received speech element information, generate speech information obtained by converting text represented by the accepted text information into speech, wherein the speech element identification information is information representing an integer and is set so that, in a case that integers represented by the speech element identification information corresponding to the speech elements are arranged in the order of arrangement of the speech elements in the speech, the integers include a pair of two adjacent integers in which an integer at the end has a different value from a value obtained by adding 1 to an integer at the beginning.