Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 223

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks

Open access
Saito, Yuki, Takamichi, Shinnosuke, Saruwatari, Hiroshi · 2018 · IEEE/ACM Transactions on Audio, Speech, and Language Processing

Abstract

A method for statistical parametric speech synthesis incorporating generative adversarial networks (GANs) is proposed. Although powerful deep neural networks techniques can be applied to artificially synthesize speech waveform, the synthetic speech quality is low compared with that of natural speech. One of the issues causing the quality degradation is an oversmoothing effect often observed in the generated speech parameters. A GAN introduced in this paper consists of two neural networks: a discriminator to distinguish natural and generated samples, and a generator to deceive the discriminator. In the proposed framework incorporating the GANs, the discriminator is trained to distinguish natural and generated speech parameters, while the acoustic models are trained to minimize the weighted sum of the conventional minimum generation loss and an adversarial loss for deceiving the discriminator. Since the objective of the GANs is to minimize the divergence (i.e., distribution difference) between the natural and generated speech parameters, the proposed method effectively alleviates the oversmoothing effect on the generated speech parameters. We evaluated the effectiveness for text-to-speech and voice conversion, and found that the proposed method can generate more natural spectral parameters and F0than conventional minimum generation error training algorithm regardless of its hyperparameter settings. Furthermore, we investigated the effect of the divergence of various GANs, and found that a Wasserstein GAN minimizing the Earth-Mover's distance works the best in terms of improving the synthetic speech quality.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/taslp.2017.2761547

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 7 references

Research works printed but not linked: 46

  1. kang, 2014, Statistical parametric speech synthesis using weighted multi-distribution deep belief network, Proc INTERSPEECH, 1959
  2. 10.1587/transinf.E97.D.1429 · DOI
  3. 10.1145/2939672.2939778 · DOI · Paper page
  4. 10.1126/science.1127647 · DOI · Paper page
  5. 10.1109/ICASSP.2015.7178816 · DOI · Paper page
  6. glorot, 2011, Deep sparse rectifier neural networks, Proc 14th Int Conf Artif Intell Statist, 315
  7. reshef, 2011, Detecting novel associations in large data sets, Science, 334, 1518, 10.1126/science.1205438 · DOI · Paper page
  8. goodfellow, 2017, NIPS 2016 tutorial: Generative adversarial networks
  9. li, 0, Generative moment matching networks, Proceedings of the 32nd Intl Conf on Machine Learning, 1718
  10. 10.1007/978-3-540-71050-9 · DOI · Paper page
  11. 10.1561/0100000004 · DOI · Paper page
  12. huang, 2015, Multi-task learning deep neural networks for speech feature denoising, Proc INTERSPEECH, 2464
  13. 10.1109/ICASSP.1988.196677 · DOI
  14. 10.1016/j.specom.2009.04.004 · DOI · Paper page
  15. 10.1109/TASL.2010.2076805 · doi:10.1109/tasl.2010.2076805
  16. 10.1515/9783110197105.515 · DOI · Paper page
  17. mao, 2017, Least squares generative adversarial networks, IEEE Int Conf Comput Vision (ICCV), 2794
  18. 10.1162/neco.2007.19.3.780 · DOI · Paper page
  19. lee, 0, Algorithms for non-negative matrix factorization, Proc Int Conf Neural Inf Process, 556
  20. takamichi, 2015, The NAIST text-to-speech system for the Blizzard Challenge 2015, Proc Blizzard Challenge Workshop
  21. toda, 2012, Implementation of computationally efficient real-time voice conversion, Proc INTERSPEECH, 94, 10.21437/Interspeech.2012-34 · doi:10.21437/interspeech.2012-34
  22. 10.21437/Interspeech.2017-1288 · DOI
  23. 10.21437/Interspeech.2016-584 · doi:10.21437/interspeech.2016-584
  24. ohtani, 2012, Histogram-based spectral equalization for HMM-based speech synthesis using mel-LSP, Proc INTERSPEECH, 1155, 10.21437/Interspeech.2012-362 · doi:10.21437/interspeech.2012-362
  25. 10.1109/TASLP.2016.2522655 · DOI
  26. 10.1109/ICASSP.2015.7178894 · DOI
  27. 10.1109/ICASSP.2016.7472749 · doi:10.1109/icassp.2016.7472749
  28. nose, 2014, Analysis of spectral enhancement using global variance in HMM-based speech synthesis, Proc INTERSPEECH, 2917
  29. zen, 2013, Statistical parametric speech synthesis using deep neural networks, Proc Int Conf Acoust Speech Signal Process, 7962
  30. goodfellow, 0, Generative adversarial nets, Proc Int Conf Neural Inf Process, 2672
  31. 10.1109/TASLP.2016.2526653 · DOI
  32. chen, 2015, Robust deep feature for spoofing detection the SJTU system for ASVspoof 2015 Challenge, Proc INTERSPEECH, 2097
  33. 10.1109/MSP.2014.2359987 · DOI · Paper page
  34. 10.1109/89.661472 · DOI · Paper page
  35. 10.1109/TASL.2007.907344 · DOI · Paper page
  36. 10.1109/JPROC.2013.2251852 · DOI · Paper page
  37. 10.1109/TASLP.2016.2551865 · DOI
  38. wu, 2006, Minimum generation error training for HMM-based speech synthesis, Proc Int Conf Acoust Speech Signal Process, 89
  39. 10.1016/S0167-6393(98)00085-5 · DOI · Paper page
  40. sagisaka, 1990, A large-scale Japanese speech database, Proc Int Conf Spoken Lang Process, 1089
  41. ohtani, 2006, Maximum likelihood voice conversion based on GMM with STRAIGHT mixed excitation, Proc INTERSPEECH, 2266
  42. kawahara, 2001, Aperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system STRAIGHT, Proc 7th Int Workshop Models Anal Vocal Emissions Biomed Appl, 1
  43. 10.1109/ICASSP.2017.7953090 · DOI
  44. 10.1016/j.specom.2015.10.007 · doi:10.1016/j.specom.2015.10.007
  45. 10.1109/ICASSP.2016.7472757 · DOI
  46. 10.21437/Interspeech.2016-522 · DOI

Cited by

See all 223

Metadata

Authors
Saito, Y., Takamichi, S., & Saruwatari, H.
Venue
IEEE/ACM Transactions on Audio, Speech, and Language Processing
Published
2018-01
Volume
26
Issue
1
Pages
84-96
ISSN
  • 2329-9290 (ISSN-L)
  • 2329-9304
OpenAlex
W2963971656
Cited by
223
References
7
FWCI
19.84
Type
journal article
Language
en
Open access
green
Funders
  • ImPACT Program of Council for Science, Technology, and Innovation (Cabinet Office, Government of Japan)
  • SECOM Science and Technology Foundation
  • JSPS KAKENHI (16H06681, JP17H06101)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks. https://app.cochat.ai/papers/10.1109/taslp.2017.2761547
The paper
Saito, Y., Takamichi, S., & Saruwatari, H. (2018). Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing. https://doi.org/10.1109/taslp.2017.2761547

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.