JPH05113795A - Voice synthesizing device - Google Patents

Abstract

PURPOSE:To produce natural and intimate synthesized voice that has been suited to one's taste by a simple operation. CONSTITUTION:A voice synthesizing device for synthesizing voice by inputting character information comprises a voice control level setting part 16 and a control code discriminating part 17 by which the values of voice control parameters such as voice velocity and voice pitch are specified so as to be suited to one's own taste and also any one of a plurality of voice control parameter combinations that have been stored in a voice control parameter storing part 18 is selected and read for collectively setting respective level values of respective voice control parameters, and the voice control parameter storing part 18 for storing the combinations of the level values of the voice control parameters that have been specified so as to suit one's taste; and the speech style for the entire sentence or for each sentence is controlled, so that more natural and intimate synthesized voice that has been suited to one's taste can be produced.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice synthesizing apparatus for inputting character string information, converting it into voice and outputting it.

[0002]

2. Description of the Related Art A speech synthesizer inputs character string information,
Since it is converted into speech and outputted, there is no limitation on the output vocabulary, so it can be expected to be applied in various fields of use as a technology that replaces recording / playback type speech synthesis.

Conventionally, as this type of speech synthesizer, there is one as shown in FIG. Reference numeral 100 in the figure is a character information input unit, which outputs to the text analysis unit 101 the character information of a kanji / kana mixed sentence input from the outside as an input text. The text analysis unit 101 generates a phoneme / prosodic symbol string from the character information input from the character information input unit 100.
Here, the phoneme / prosodic symbol string is a string (intermediate language) in which the reading, accent, intonation, etc. of the input sentence are described as a character string.

Reference numeral 102 is a pronunciation dictionary in which the readings and accents of words are registered. The text analysis unit 101 refers to the pronunciation dictionary 102 to generate phonological / prosodic symbol strings.

A synthesis parameter generation unit 103 refers to a phoneme unit memory 104 composed of a ROM or the like for accumulating voice units and the like, and refers to a phoneme / prosodic symbol string from the text analysis unit 101 to identify a phoneme unit. A synthetic parameter including patterns such as a piece (sound type), phoneme duration (sound length), and fundamental frequency (voice pitch) is generated. here,
A voice unit is a basic unit of voice for connecting to create a synthetic waveform, and there are various voice units depending on the type of sound.

Reference numeral 105 denotes a voice synthesizing section, which produces a synthetic waveform based on the synthesis parameters produced by the synthesis parameter producing section 103, and outputs synthetic speech through the speaker 106.

On the other hand, most of this type of speech synthesizer has a function of changing the synthesized voice to a user's favorite timbre, such as vocal speed, voicing intensity, pitch, and intonation (hereinafter referred to as "voice control"). "Parameters") can be set by selecting from each of several levels. The level of the voice control parameter is specified by inserting a special character code (for example, a level specifying special code shown in FIG. 3) that is fixed by the user into the input text.

The special character code for level setting of the inserted voice control parameter is decoded by the voice control level setting unit (not shown), and the level of each control parameter is set.

[0009]

By the way, the timbre of choice differs from person to person. In addition, the utterance style changes depending on the utterance content in the actual natural voice, and in order to make the synthetic voice more natural, a different utterance style is set for each sentence for each case. There is a need.

However, in the speech synthesizer having the above-mentioned structure, when various timbres and utterance styles are to be realized by adjusting the utterance speed, utterance intensity, pitch, etc. Levels such as intensity, pitch, and intonation must be specified, so if multiple users synthesize voices with their favorite tones, or if different sentences have different utterance styles, level The specified operation is very complicated.

In addition, although it takes a lot of effort to finely adjust each voice control parameter to realize an intended utterance style, even if the value of the voice control parameter once determined realizes another utterance style. There is a problem that if the value is changed, it will be discarded at that point.

The present invention has been made in consideration of the above problems, and provides a voice synthesizing device capable of instantly generating a synthetic voice having a utterance content or a utterance style intended by a user with a simple operation. The purpose is to

[0013]

In order to solve such a problem, the present invention relates to a voice synthesizing apparatus for synthesizing a voice by inputting character information. In such a voice synthesizer, a designation means for designating a voice control parameter value such as a speaking rate, a speaking intensity, a voice pitch, and an intonation level according to one's own preference, and a speech control parameter designated by this designating means. Voice control parameter storage means for storing a combination of level values and arbitrary one of a plurality of voice control parameter combinations stored in the voice control parameter storage means are selected and read out, and each level value of each voice control parameter is selected. And a level value setting means for collectively setting.

[0014]

The level value of the voice control parameter is selected and designated by the designating means in accordance with one's own preference and stored in the voice control parameter storing means. Then, any one of the combinations of the plurality of voice control parameters stored in the voice control parameter storage means is selected and read out, and the level value setting means collectively sets each level value of the voice control parameters. As a result, a synthetic voice having the utterance content or the utterance style intended by the user is immediately generated by a simple operation.

[0015]

Embodiments of the present invention will be described in detail below with reference to FIGS. 1 and 4. FIG. 1 is a block diagram showing a speech synthesizer according to this embodiment, and FIG. 4 is a configuration diagram showing a speech control parameter storage unit.

This speech synthesizer comprises a character information input section 1
0, text analysis unit 11, pronunciation dictionary 12, synthesis parameter generation unit 13, speech unit memory 14, speech synthesis unit 15,
Although it is similar to the conventional voice synthesizer in that it has a speaker 19, the voice synthesizer of this embodiment further includes a voice control level setting unit 16, a control code discriminating unit 17, and a voice control parameter storage unit 18. There is. In addition to the input text, the character information from the character information input unit 10 includes a special code for setting the level value of the voice control parameter.

The voice control level setting unit 16 has a temporary storage area (not shown) therein, and holds the level value of each voice control parameter set by a special code in this temporary storage area. Adjust the values to your liking.

The control code discriminating section 17 discriminates the special code in the character information and outputs it to the voice control level setting section 16. Here, the special code is a code for setting the level value of the voice control parameter.
A save command, which is an instruction command for storing (saving) the set level value of the voice control parameter in the voice control parameter storage unit 18, and a read command for specifying and reading the level value of the saved voice control parameter. included.

As shown in FIG. 4, the voice control parameter storage unit 18 is composed of a plurality of areas, and for each area, the utterance speed, utterance intensity, voice pitch set in accordance with one's own preference, The level value of the voice control parameter such as the amount of intonation is stored.

Then, the special code in the character information is discriminated and outputted to the voice control level setting section 16, and the level value of the voice control parameter is set by the special code from the discrimination section 17. The voice control level setting unit 16 constitutes a designating unit, and the voice control parameter storage unit 18 constitutes a voice control parameter storing unit. Further, the read command in the character information is discriminated and outputted to the voice control level setting unit 16, and the level value stored in the voice control parameter storage unit 18 is read by the read command from the discriminating unit 17. A level setting means is constituted by the voice control level setting unit 16 for setting each voice control parameter.

The speech synthesizer of this embodiment is constructed as described above, and its operation will be described below.

The processing from the character information input unit 10 to the voice synthesizing unit 15 is the same as that of the conventional voice synthesizing apparatus described above, and the input text (kanji mixed kana sentence) as the character information input from the character information input unit 10 is used. Is analyzed by the text analysis unit 11 with reference to the pronunciation dictionary 12 and converted into a phoneme / prosodic symbol string. The synthesis parameter generation unit 13 generates synthesis parameters such as a phoneme, phoneme duration, and fundamental frequency pattern based on the phoneme / prosodic symbol string. The voice synthesizer 15 generates a synthesized waveform based on the synthesis parameter and outputs the synthesized voice from the speaker 19.

On the other hand, the character information (input text) from the character information input unit 10 is sent to the text analysis unit 11 and also to the control code discrimination unit 17. The control code discriminating unit 17 discriminates the special code to be input prior to the input text or embedded in the input text and sends it to the voice control level setting unit 16. In the voice control level setting unit 16, the level value of each voice control parameter is set by the special code, and the level value is held in the temporary storage area and is sent to the synthesis parameter generation unit 13 and the voice synthesis unit 15, and this voice Synthetic voice is generated based on the level value of the control parameter and output from the speaker 19.

The user adjusts according to his / her favorite tone color and utterance style while confirming the synthesized voice output from the speaker 19 by this voice synthesis operation. That is, of the synthetic voice to be output, the portion to be changed is input by the special code, and the level values of the respective voice control parameters are adjusted by the operations of the control code discrimination unit 17 and the voice control level setting unit 16. Further, the tone color and the utterance style are changed for each sentence, and fine adjustments are made according to one's own preference, and stored in the temporary storage area.

Finally, when the fine adjustment of the level value of the voice control parameter is completed, the save command is input. By this save command, the level value stored in the temporary storage area is saved (stored) in the voice control parameter storage unit 18. When setting a plurality of utterance styles, the above operation is repeated.

When generating a synthetic voice, the user inputs a read command instructing the utterance style intended by the user, and the read command causes the level value of the voice control parameter stored in the voice control parameter storage unit 18 to be set. read out. Then, the read level value is output to the synthesis parameter generation unit 13 and the voice synthesis unit 15 to generate the synthesized voice intended by the user.

[0027]

As described above in detail, according to the voice synthesizer of the present invention, a plurality of combinations of voice control parameters uniquely set by the user are stored, and an arbitrary combination is selected from the combinations. Since one is selected and read and the level value of each voice control parameter is set collectively, once the level value of each voice control parameter is set, the user can set the level value of each voice control parameter. It is possible to easily perform voice synthesis according to one's preference by a simple operation without setting values one by one.

If level values of a plurality of voice control parameters are created in advance according to a plurality of utterance styles, it is possible to easily realize voice synthesis while changing the utterance style according to a sentence. The sound will be more natural and familiar.

[Brief description of drawings]

FIG. 1 is a block diagram showing a speech synthesizer according to the present embodiment.

FIG. 2 is a block diagram showing a conventional speech synthesizer.

FIG. 3 is a table showing a special code for specifying a level of a voice control parameter.

FIG. 4 is a configuration diagram showing a voice control parameter storage unit.

[Explanation of symbols]

 10 character information input unit 11 text analysis unit 12 pronunciation dictionary 13 synthesis parameter generation unit 14 speech unit memory 15 voice synthesis unit 16 voice control level setting unit 17 control code determination unit 18 voice control parameter storage unit 19 speaker

Claims (1)

[Claims] 1. A voice synthesizing device for synthesizing a voice by inputting character information, which specifies voice control parameter values such as a voicing speed, a voicing intensity, a voice pitch, and an intonation level according to one's own preference. Specifying means, a voice control parameter storage means for storing a combination of the level values of the voice control parameters designated by the specifying means, and an arbitrary one of a combination of a plurality of voice control parameters stored in the voice control parameter storage means. A voice synthesizing apparatus comprising: a level value setting unit that selects and reads out one of the voice control parameters and sets each level value of each voice control parameter collectively.