SPEECH PROCESSING APPARATUS AND SPEECH SYNTHESIS APPARATUS

• US 20090144053A1
• Filed: 12/03/2008
• Published: 06/04/2009
• Est. Priority Date: 12/03/2007
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Digital Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: KAGOSHIMA, Takehiko, TSUCHIYA, Katsumi, TAMURA, Masatsune
• Granted Patent: US 8,321,208 B2
• Time in Patent Office: Days
• US Class Current: 704/207
• CPC Class Codes: G10L 13/06 Elementary speech units used in speech synthesisers; Concatenation rules

Abstract

An information extraction unit extracts spectral envelope information of L-dimension from each frame of speech data. The spectral envelope information does not have a spectral fine structure. A basis storage unit stores N bases (L>N>1). Each basis is differently a frequency band having a maximum as a peak frequency in a spectral domain having L-dimension. A value corresponding to a frequency outside the frequency band along a frequency axis of the spectral domain is zero. Two frequency bands of which two peak frequencies are adjacent along the frequency axis partially overlap. A parameter calculation unit minimizes a distortion between the spectral envelope information and a linear combination of each basis with a coefficient by changing the coefficient, and sets the coefficient of each basis from which the distortion is minimized to a spectral envelope parameter of the spectral envelope information.

Claims

1. An apparatus for a speech processing, comprising:

a frame extraction unit configured to extract a speech signal in each frame;

an information extraction unit configured to extract a spectral envelope information of L-dimension from each frame, the spectral envelope information not having a spectral fine structure;

a basis storage unit configured to store N bases (L>

N>

1), each basis being differently a frequency band having a maximum as a peak frequency in a spectral domain having L-dimension, a value corresponding to a frequency outside the frequency band along a frequency axis of the spectral domain being zero, two frequency bands of which two peak frequencies are adjacent along the frequency axis partially overlapping; and

a parameter calculation unit configured to minimize a distortion between the spectral envelope information and a linear combination of each basis with a coefficient by changing the coefficient, and to set the coefficient of each basis from which the distortion is minimized to a spectral envelope parameter of the spectral envelope information.

2. The apparatus according to claim 1, further comprising:

a basis generation unit configured to determine a plurality of peak frequencies in the spectral domain, to create a unimodal window function having a length as an interval between two adjacent peak frequencies and having all zero frequency outside three adjacent peak frequencies along the frequency axis, and to set a shape of the window function to the basis.

3. The apparatus according to claim 2, wherein

the basis generation unit determines the peak frequency having a wider interval from adjacent peak frequency when the frequency is higher along the frequency axis.

4. The apparatus according to claim 2, wherein

the basis generation unit determines the peak frequency having a wider interval from adjacent peak frequency when the frequency is higher along the frequency axis as for a frequency band lower than a boundary frequency on the frequency axis, and determines the peak frequency having an equal interval from adjacent peak frequency as for a frequency band higher than the boundary frequency.

5. The apparatus according to claim 1, further comprising:

a basis generation unit configured to extract spectral envelope information from a speech signal to generate basis, to minimize a first evaluation function by changing the basis and the coefficient, the first evaluation being the sum of an error term and a first regularization term, the error term being a distortion between the spectral envelope information and a linear combination of the basis with the coefficient, the first regularization term being a sparseness of the coefficient, the sparseness being a smaller value when the coefficient is closer to zero, and to select the basis from which the first evaluation function is minimized.

6. The apparatus according to claim 5, wherein

the basis generation unit minimizes a second evaluation function by changing the basis and the coefficient, the second evaluation function being the sum of the error term, the first regularization term and a second regularization term, the second regularization term being a concentration degree at a position to a center of the basis, the concentration degree being a larger value when a value at the position distant from the center of the basis is larger, and to select the basis from which the second evaluation function is minimized.

7. The apparatus according to claim 1, wherein

the distortion is a squared error between the spectral envelope information and a linear combination of each basis with the coefficient corresponding to each basis.

8. The apparatus according to claim 1, wherein

the parameter calculation unit minimizes the distortion under a constraint that the coefficient is non-negative.

9. The apparatus according to claim 1, wherein

the parameter calculation unit assigns a number of quantized bits to each dimension of the spectral envelope parameter, determines a number of quantization bits to each dimension of the spectral envelope parameter, and quantizes the spectral envelope parameter based on the number of quantized bits and the number of quantization bits.

10. The apparatus according to claim 1, wherein

the spectral envelope information is one of a logarithm spectral envelope, a phase spectral, an amplitude spectral envelope, and a power spectral envelope.

11. An apparatus for a speech synthesis, comprising:

an acquisition unit configured to acquire a spectral envelope parameter corresponding to a pitch-cycle waveform of each speech unit to be synthesized as a speech, the spectral envelope parameter having L-dimension;

a basis storage unit configured to store N bases (L>

N>

1), each basis being differently a frequency band having a maximum as a peak frequency in a spectral domain having L-dimension, a value corresponding to a frequency outside the frequency band along a frequency axis of the spectral domain being zero, two frequency bands of which two peak frequencies are adjacent along the frequency axis partially overlapping;

an envelope generation unit configured to generate a spectral envelope information by linearly combining the basis with the spectral envelope parameter;

a pitch-cycle waveform generation unit configured to generate a plurality of pitch-cycle waveforms by inverse-Fourier transform with a spectral of the spectral envelope information; and

a speech generation unit configured to generate a plurality of speech units by overlapping and adding the plurality of pitch-cycle waveforms, and to generate a speech waveform by concatenating the plurality of speech units.

12. The apparatus according to claim 11, further comprising:

a parameter storage unit configured to store the spectral envelope parameter corresponding to a pitch-cycle waveform of each speech unit;

an attribute storage unit configured to store an attribute information of each speech unit;

a division unit configured to divide a phoneme sequence of input text into each synthesis unit; and

a selection unit configured to select at least one speech unit corresponding to each synthesis unit by using the attribute information.

13. The apparatus according to claim 12, wherein

the acquisition unit acquires the spectral envelope parameter corresponding to the pitch-cycle waveform of the speech unit selected by the selection unit.

14. The apparatus according to claim 13, further comprising:

a fusion unit configured to fuse a plurality of spectral envelope parameters to one spectral envelope parameter, when the acquisition unit acquires the plurality of spectral envelope parameters corresponding to pitch-cycle waveforms of a plurality of selected speech units by the selection unit.

15. The apparatus according to claim 14, wherein

the fusion unit corresponds the spectral envelope parameter of each speech unit along a temporal direction, averages corresponded spectral envelope parameters to generate an averaged spectral envelope parameter, selects one representative speech unit from the plurality of speech units, and set the spectral envelope parameter of the one representative speech unit as a representative spectral envelope parameter.

16. The apparatus according to claim 15, wherein

the fusion unit determines a boundary order from the representative spectral envelope parameter or the averaged spectral envelope parameter, and mixes the plurality of spectral envelope parameters by using the averages spectral envelope parameter for a spectral envelope parameter having lower order than the boundary order and by using the representative spectral envelope parameter for a spectral envelope parameter having higher order than the boundary order.

17. A method for a speech processing, comprising:

dividing a speech signal into each frame;

extracting a spectral envelope information of L-dimension from each frame, the spectral envelope information not having a spectral fine structure;

storing N bases (L>

N>

1) in a memory, each basis being differently a frequency band having a maximum as a peak frequency in a spectral domain having L-dimension, a value corresponding to a frequency outside the frequency band along a frequency axis of the spectral domain being zero, two frequency bands of which two peak frequencies are adjacent along the frequency axis partially overlapping;

minimizing a distortion between the spectral envelope information and a linear combination of each basis with a coefficient by changing the coefficient; and

setting the coefficient of each basis from which the distortion is minimized to a spectral envelope parameter of the spectral envelope information.

18. A method for a speech synthesis, comprising:

acquiring a spectral envelope parameter corresponding to a pitch-cycle waveform of each speech unit to be synthesized as a speech, the spectral envelope parameter having L-dimension;

storing N bases (L>

N>

1) in a memory, each basis being differently a frequency band having a maximum as a peak frequency in a spectral domain having L-dimension, a value corresponding to a frequency outside the frequency band along a frequency axis of the spectral domain being zero, two frequency bands of which two peak frequencies are adjacent along the frequency axis partially overlapping;

generating a spectral envelope information by linearly combining the basis with the spectral envelope parameter;

generating a plurality of pitch-cycle waveforms by inverse-Fourier transform with a spectral of the spectral envelope information;

generating a plurality of speech units by overlapping and adding the plurality of pitch-cycle waveforms; and

generating a speech waveform by concatenating the plurality of speech units.

19. A computer program stored in a computer readable medium for causing a computer to perform a method for a speech processing, the method comprising:

dividing a speech signal into each frame;

extracting a spectral envelope information of L-dimension from each frame, the spectral envelope information not having a spectral fine structure;

storing N bases (L>

N>

1) in a memory, each basis being differently a frequency band having a maximum as a peak frequency in a spectral domain having L-dimension, a value corresponding to a frequency outside the frequency band along a frequency axis of the spectral domain being zero, two frequency bands of which two peak frequencies are adjacent along the frequency axis partially overlapping;

minimizing a distortion between the spectral envelope information and a linear combination of each basis with a coefficient by changing the coefficient; and

setting the coefficient of each basis from which the distortion is minimized to a spectral envelope parameter of the spectral envelope information.

20. A computer program stored in a computer readable medium for causing a computer to perform a method for a speech synthesis, the method comprising:

acquiring a spectral envelope parameter corresponding to a pitch-cycle waveform of each speech unit to be synthesized as a speech, the spectral envelope parameter having L-dimension;

storing N bases (L>

N>

1) in a memory, each basis being differently a frequency band having a maximum as a peak frequency in a spectral domain having L-dimension, a value corresponding to a frequency outside the frequency band along a frequency axis of the spectral domain being zero, two frequency bands of which two peak frequencies are adjacent along the frequency axis partially overlapping;

generating a spectral envelope information by linearly combining the basis with the spectral envelope parameter;

generating a plurality of pitch-cycle waveforms by inverse-Fourier transform with a spectral of the spectral envelope information;

generating a plurality of speech units by overlapping and adding the plurality of pitch-cycle waveforms; and

generating a speech waveform by concatenating the plurality of speech units.