JP2009037214A5 - - Google Patents

Claims (10)

A speech processing device capable of reproducing a sentence composed of a plurality of words or phrases using a recording / playback method or a rule synthesis method,
A specifying means for specifying whether each of a plurality of words or phrases constituting a sentence to be reproduced is a word or phrase reproduced by a recording and reproduction method or a word or phrase reproduced by a rule composition method;
When each of the plurality of words or phrases is reproduced in the first arrangement order using the reproduction method specified by the specifying means, reproduction using the recording / reproduction method and reproduction using the rule composition method are performed. Selection means for selecting whether to reproduce each of the plurality of words or phrases in the first arrangement order or in an arrangement order different from the first arrangement order based on the number of inversions to be switched;
Reproducing means for reproducing each of the plurality of words or phrases in the arrangement order selected by the selecting means using the reproducing method specified by the specifying means.   The number of inversions corresponds to the sum of the number of times of switching from playback using the recording and playback method to playback using the rule synthesis method and the number of times switching from playback using the rule synthesis method to playback using the recording and playback method. The speech processing apparatus according to claim 1.   The selection means selects reproduction based on the first arrangement order when the number of inversions is less than a predetermined number, and reproduces reproduction based on an arrangement order different from the first arrangement order when the number is greater than the predetermined number. The audio processing apparatus according to claim 1, wherein the audio processing apparatus is selected.   The selection means selects reproduction based on the first arrangement order when the number of inversions is less than a predetermined number, and selects the first arrangement order based on a predetermined criterion when the number of inversions is greater than the predetermined number. The audio processing apparatus according to claim 1, wherein reproduction is selected according to any one of a plurality of different arrangement orders.   When the number of inversions is equal to or greater than the predetermined number, the selection unit is configured to perform playback using the recording / playback method and playback using the rule composition method among a plurality of placement orders different from the first placement order. The audio processing apparatus according to claim 4, wherein reproduction according to an arrangement order in which the number of times of switching is less than the predetermined number is selected. A speech processing device that generates speech of guidance according to a user operation using speech synthesis means capable of performing speech synthesis while selectively switching between a recording and playback method and a rule synthesis method,
A first guidance comprising a fixed part indicating a fixed message, and a variable part positioned in the middle of the fixed part and indicating that a message according to a user operation is inserted; and Guidance holding means for holding second guidance having the same meaning as the first guidance located at the end;
Entry holding means for holding a set of entries that can be registered with a notation, a reading of the notation, and a sound of the reading, which are associated with a user operation;
Obtaining means for obtaining an entry corresponding to an operation performed by the user from the entry holding means;
Have
The speech synthesis means
When the voice is registered in the entry acquired by the acquisition unit, the first guidance is selected, and the voice corresponding to the fixed part recorded in advance is used for the fixed part of the first guidance. In addition to performing voice synthesis with the recording and playback method, the voice synthesis is performed with the recording and playback method using the voice registered in the entry for the variable part,
If no voice is registered in the entry acquired by the acquisition means, the second guidance is selected, and the voice corresponding to the fixed part recorded in advance is used for the fixed part of the second guidance. A voice processing apparatus characterized in that voice synthesis is performed by a recording / playback system, and voice synthesis is performed by a rule synthesis system for a variable part. A communication means for performing network communication;
The voice processing apparatus according to claim 6, wherein the user operation includes an operation related to the network communication, and the entry holding unit constitutes an address book for the network communication. A first guidance comprising a fixed part indicating a fixed message, and a variable part positioned in the middle of the fixed part and indicating that a message according to a user operation is inserted; and Guidance holding means that holds the second guidance that is synonymous with the first guidance positioned at the end, and a set of entries that can be associated with a user operation and that can register the notation, the reading of the notation, and the sound of the reading And a speech processing unit that can perform speech synthesis while selectively switching between the recording / playback method and the rule synthesis method. A voice processing method for generating a voice of guidance,
Acquisition means, from the entry holding means, an acquisition step of acquiring an entry corresponding to the operation performed by the user,
When the voice synthesizing means has a voice registered in the entry acquired in the acquisition step, the first guidance is selected, and the fixed portion of the first guidance corresponds to the fixed portion recorded in advance. A first voice synthesis step of performing voice synthesis by voice recording using a recording / playback method and voice synthesis by voice recording using a voice registered in the entry for the variable unit;
When the voice synthesizing means has no voice registered in the entry acquired in the acquiring step, the second guidance is selected, and the fixed part of the second guidance corresponds to the fixed part recorded in advance. A second voice synthesis step of performing voice synthesis by a recording / playback method using the voice to be played and voice synthesis by a rule synthesis method for the variable portion;
A voice processing method characterized by comprising: The program for making a computer perform each process of the audio | voice processing method of Claim 8.   A computer-readable storage medium storing the program according to claim 9.