Expressivity of voice synthesis

• US 20020026315A1
• Filed: 06/01/2001
• Published: 02/28/2002
• Est. Priority Date: 06/02/2000
• Status: Active Grant

• Current Assignee: Sony France SA (Sony Group Corp.)
• Original Assignee: Sony France SA (Sony Group Corp.)
• Inventors: Miranda, Eduardo Reck
• Granted Patent: US 6,804,649 B2
• Time in Patent Office: Days
• US Class Current: 704/258
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: G10L 13/07 Concatenation rules

Abstract

Voice synthesis with improved expressivity is obtained in a voice synthesiser of source-filter type by making use of a library of source sound categories in the source module. Each source sound category corresponds to a particular morphological category and is derived from analysis of real vocal sounds, by inverse filtering so as to subtract the effect of the vocal tract. The library may be parametrical, that is, the stored data corresponds not to the inverse-filtered sounds themselves but to synthesis coefficients for resynthesising the inverse-filtered sounds using any suitable re-synthesis technique, such as the phase vocoder technique. The coefficients are derived by STFT analysis.

Claims

1. Voice synthesiser apparatus comprising:

a source module adapted to output, during use, a source signal;

a filter module arranged to receive said source signal as an input and to apply thereto a filter characteristic modelling the response of the vocal tract;

characterised in that the source module comprises a library of stored representations of source sound categories each corresponding to a respective morphological category, and the source signal output by the source module corresponds to a stored representation of a selected source sound category.

2. Voice synthesiser apparatus according to claim 1, wherein the source module comprises a resynthesis device adapted to output said source signal and the stored representations in said library are in the form of resynthesis coefficients enabling said source sound categories to be regenerated by the resynthesis device.

3. Voice synthesis apparatus according to claim 2, wherein the stored representations in said library are derived by inverse filtering real vocal sounds so as to subtract the articulatory effects imposed by the vocal tract.

4. Voice synthesis apparatus according to claim 3, wherein the stored representations in said library are derived by deconvoluting respective portions of an utterance.

5. Voice synthesis apparatus according to claim 3, wherein the stored representation corresponding to a particular morphological category is derived by averaging signals produced by inverse filtering a plurality of examples of vocal sounds embodying the morphological category.

6. Voice synthesis apparatus according to claim 2, wherein the resynthesis device comprises a phase vocoder adapted to output glottal signals for submission to said filter module, and the resynthesis coefficients constituting the stored representation of a source sound category correspond to a representation derived by STFT analysis of signals resulting from the inverse filtering.

7. Voice synthesis apparatus according to claim 6, and comprising means for performing spectral transformations on said resynthesis coefficients, wherein the phase vocoder is driven by the transformed resynthesis coefficients.

8. Voice synthesis apparatus according to claim 1, wherein the pitch of the source signal varies as a function of time, and there is provided means for transforming the source signal by modifying the pitch variation function, the filter module being adapted to operate on the source signal after transformation thereof by said transforming means.

9. Voice synthesis apparatus according to claim 1, wherein the filter module is implemented using the waveguide ladder technique.

10. A method of voice synthesis comprising the steps of:

providing a source module,

causing said source module to generate a source signal corresponding to a particular morphological category of sound,

providing a filter module having a filter characteristic modelling the response of the vocal tract;

inputting the source signal to the filter module

characterised in that the step of providing a source module comprises providing a source module comprising a library of stored representations of source sound categories each corresponding to a respective morphological category, and the source signal output by the source module corresponds to a stored representation of a selected source sound category.

11. A voice synthesis method according to claim 10, wherein the source module outputs a source signal by retrieval from the library of a stored representation in the form of resynthesis coefficients representing the corresponding morphological category, input of the retrieved resynthesis coefficients to a resynthesis device, and output of the signal generated by the resynthesis device as the source signal.

12. A voice synthesis method according to claim 11, wherein the stored representations in said library are derived by inverse filtering real vocal sounds so as to subtract the articulatory effects imposed by the vocal tract.

13. A voice synthesis method according to claim 12, wherein the stored representations in said library are derived by deconvoluting respective portions of an utterance.

14. A voice synthesis method according to claim 12, wherein the stored representation corresponding to a particular morphological category is derived by averaging signals produced by inverse filtering a plurality of examples of vocal sounds embodying the morphological category.

15. A voice synthesis method according to claim 11, wherein the resynthesis device comprises a phase vocoder adapted to output glottal signals to said filter module, and the resynthesis coefficients constituting the stored representation of a source sound category correspond to a representation derived by STFT analysis of signals resulting from the inverse filtering.

16. A voice synthesis method according to claim 15, wherein a spectral transformation is applied to the retrieved resynthesis coefficients, and the transformed coefficients are used to drive the phase vocoder.

17. A voice synthesis method according to claim 10, wherein the pitch of the source signal varies as a function of time, and comprising the step of transforming the source signal by modifying the pitch variation function, the filter module being adapted to operate on the source signal after transformation thereof in said transforming step.

18. A voice synthesis method according to claim 10, wherein the filter module is implemented using the waveguide ladder technique.