Strained-rough-voice conversion device, voice conversion device, voice synthesis device, voice conversion method, voice synthesis method, and program

A voice conversion device comprising:

• one or more processors executing:
• a receiving unit configured to receive a speech waveform;
• a strained phoneme position designation unit configured to designate a phoneme to be converted to a strained rough voice;
• and
• a modulation unit configured to perform, in accordance with the phoneme to be converted to the strained rough voice designated by said strained phoneme position designation unit, amplitude modulation on the speech waveform so as to periodically fluctuate a curved outline of the speech waveform, the speech waveform expressing the phoneme designated by said strained phoneme position designation unit,
• wherein the amplitude modulation performed by said modulation unit on the speech waveform includes performing periodic amplitude fluctuation on the speech waveform by multiplying (i) the speech waveform expressing the phoneme designated by said strained phoneme position designation unit by (ii) a periodic fluctuation signal, the periodic fluctuation signal being generated according to a distribution of a fluctuation frequency of an amplitude envelope of a strained rough voice, the fluctuation frequency being a mode value of a frequency calculated for each of a plurality of points over a sampling period of the amplitude envelope of the strained rough voice, and the periodic fluctuation signal having one of frequencies in a range of 40 Hz to 120 Hz, and
• wherein the frequency of the periodic fluctuation signal is different from the fundamental frequency of the speech waveform expressing the phoneme designated by said strained phoneme position designation unit.

A voice conversion device comprising:

• one or more processors executing:
• a receiving unit configured to receive a speech waveform;
• a strained phoneme position input unit configured to receive, from a user, an input designating the phoneme to be converted to the strained rough voice;
• and
• a modulation unit configured to perform, in accordance with the input designating the phoneme to be converted to the strained rough voice received by said strained phoneme position input unit, amplitude modulation on the speech waveform so as to periodically fluctuate a curved outline of the speech waveform, the speech waveform expressing the phoneme designated by the input from the user,
• wherein the amplitude modulation performed by said modulation unit on the speech waveform includes performing periodic amplitude fluctuation on the speech waveform by multiplying (i) the speech waveform expressing the phoneme designated by the input from the user by (ii) a periodic fluctuation signal, the periodic fluctuation signal being generated according to a distribution of a fluctuation frequency of an amplitude envelope of a strained rough voice, the fluctuation frequency being a mode value of a frequency calculated for each of a plurality of points over a sampling period of the amplitude envelope of the strained rough voice, and the periodic fluctuation signal having one of frequencies in a range of 40 Hz to 120 Hz, and
• wherein the frequency of the periodic fluctuation signal is different from the fundamental frequency of the speech waveform expressing the phoneme designated by the input from the user.

A voice synthesis device comprising:

• one or more processors executing:
• a receiving unit configured to receive a text;
• a language processing unit configured to analyze the text received by said receiving unit to generate pronunciation information and prosody information;
• a voice synthesis unit configured to synthesize a speech waveform according to the pronunciation information and the prosody information;
• a strained phoneme position designation unit configured to designate, in the speech waveform, a phoneme to be converted to a strained rough voice;
• and
• a modulation unit configured to perform, in accordance with the phoneme to be converted to the strained rough voice designated by said strained phoneme position designation unit, amplitude modulation on the speech waveform so as to periodically fluctuate a curved outline of the speech waveform, the speech waveform expressing the phoneme designated by said strained phoneme position designation unit,
• wherein the amplitude modulation performed by said modulation unit on the speech waveform includes performing periodic amplitude fluctuation on the speech waveform by multiplying (i) the speech waveform expressing the phoneme designated by said strained phoneme position designation unit by (ii) a periodic fluctuation signal, the periodic fluctuation signal being generated according to a distribution of a fluctuation frequency of an amplitude envelope of a strained rough voice, the fluctuation frequency being a mode value of a frequency calculated for each of a plurality of points over a sampling period of the amplitude envelope of the strained rough voice, and the periodic fluctuation signal having one of frequencies in a range of 40 Hz to 120 Hz, and
• wherein the frequency of the periodic fluctuation signal is different from the fundamental frequency of the speech waveform expressing the phoneme designated by said strained phoneme position designation unit.

A voice conversion method comprising:

• designating a phoneme to be converted to a strained rough voice in a speech;
• and
• performing, using a processor, amplitude modulation on a speech waveform so as to periodically fluctuate a curved outline of the speech waveform, the speech waveform expressing the phoneme designated in said designating,
• wherein the amplitude modulation performed in said modulating on the speech waveform includes performing periodic amplitude fluctuation on the speech waveform by multiplying (i) the speech waveform expressing the phoneme designated in said designating by (ii) a periodic fluctuation signal, the periodic fluctuation signal being generated according to a distribution of a fluctuation frequency of an amplitude envelope of a strained rough voice, the fluctuation frequency being a mode value of a frequency calculated for each of a plurality of points over a sampling period of the amplitude envelope of the strained rough voice, and the periodic fluctuation signal having one of frequencies in a range of 40 Hz to 120 Hz, and
• wherein the frequency of the periodic fluctuation signal is different from the fundamental frequency of the speech waveform expressing the phoneme designated in said designating.

A voice synthesis method comprising:

• designating a phoneme to be converted to a strained rough voice;
• and
• generating, using a processor, a synthetic speech by performing amplitude modulation on a speech waveform so as to periodically fluctuate a curved outline of the speech waveform, the speech waveform expressing the phoneme designated in said designating,
• wherein the amplitude modulation performed in said modulating on the speech waveform includes performing periodic amplitude fluctuation on the speech waveform by multiplying (i) the speech waveform expressing the phoneme designated in said designating by (ii) a periodic fluctuation signal, the periodic fluctuation signal being generated according to a distribution of a fluctuation frequency of an amplitude envelope of a strained rough voice, the fluctuation frequency being a mode value of a frequency calculated for each of a plurality of points over a sampling period of the amplitude envelope of the strained rough voice, and the periodic fluctuation signal having one of frequencies in a range of 40 Hz to 120 Hz, and
• wherein the frequency of the periodic fluctuation signal is different from the fundamental frequency of the speech waveform expressing the phoneme designated in said designating.

A non-transitory computer readable recording medium having stored thereon a voice conversion program, wherein, when executed, said voice conversion program causes a computer to execute a method comprising:

• designating a phoneme to be converted to a strained rough voice in a speech;
• and
• performing amplitude modulation on a speech waveform so as to periodically fluctuate a curved outline of the speech waveform, the speech waveform expressing the phoneme designated in said designating,
• wherein the amplitude modulation performed in said modulating on the speech waveform includes performing periodic amplitude fluctuation on the speech waveform by multiplying (i) the speech waveform expressing the phoneme designated in said designating by (ii) a periodic fluctuation signal, the periodic fluctuation signal being generated according to a distribution of a fluctuation frequency of an amplitude envelope of a strained rough voice, the fluctuation frequency being a mode value of a frequency calculated for each of a plurality of points over a sampling period of the amplitude envelope of the strained rough voice, and the periodic fluctuation signal having one of frequencies in a range of 40 Hz to 120 Hz, and
• wherein the frequency of the periodic fluctuation signal is different from the fundamental frequency of the speech waveform expressing the phoneme designated in said designating.

A non-transitory computer readable recording medium having stored thereon a voice synthesis program, wherein, when executed, said voice synthesis program causes a computer to execute a method comprising:

• designating a phoneme to be converted to a strained rough voice;
• and
• generating a synthetic speech by performing amplitude modulation on a speech waveform so as to periodically fluctuate a curved outline of the speech waveform, the speech waveform expressing the phoneme designated in said designating,
• wherein the amplitude modulation performed in said modulating on the speech waveform includes performing periodic amplitude fluctuation on the speech waveform by multiplying (i) the speech waveform expressing the phoneme designated in said designating by (ii) a periodic fluctuation signal, the periodic fluctuation signal being generated according to a distribution of a fluctuation frequency of an amplitude envelope of a strained rough voice, the fluctuation frequency being a mode value of a frequency calculated for each of a plurality of points over a sampling period of the amplitude envelope of the strained rough voice, and the periodic fluctuation signal having one of frequencies in a range of 40 Hz to 120 Hz, and
• wherein the frequency of the periodic fluctuation signal is different from the fundamental frequency of the speech waveform expressing the phoneme designated in said designating.

A strained-rough-voice conversion device comprising:

• one or more processors executing:
• a strained phoneme position designation unit configured to designate a phoneme to be converted to a strained rough voice in a speech;
• and
• a modulation unit configured to perform amplitude modulation on a sound source signal of a speech waveform so as to periodically fluctuate a curved outline of the speech waveform, the speech waveform expressing the phoneme designated by said strained phoneme position designation unit,
• wherein the amplitude modulation performed by said modulation unit on the sound source signal includes performing periodic amplitude fluctuation on the sound source signal by multiplying (i) the sound source signal expressing the phoneme designated by said strained phoneme position designation unit by (ii) a periodic fluctuation signal, the periodic fluctuation signal being generated according to a distribution of a fluctuation frequency of an amplitude envelope of a strained rough voice, the fluctuation frequency being a mode value of a frequency calculated for each of a plurality of points over a sampling period of the amplitude envelope of the strained rough voice, and the periodic fluctuation signal having one of frequencies in a range of 40 Hz to 120 Hz, and
• wherein the frequency of the periodic fluctuation signal is different from the fundamental frequency of the sound source signal expressing the phoneme designated by said strained phoneme position designation unit.