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 accessAbstract
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.
Integrity signals
Registry
Cites
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.
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
WaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., & Metaxas, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.629 · Cited by 3,021
Generative Adversarial Text to Image Synthesis
Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., & Lee, H. (2016) · arXiv · doi:10.48550/arxiv.1605.05396 · Cited by 2,494
Arjovsky, M., Chintala, S., & Bottou, L. (2017) · arXiv · doi:10.48550/arxiv.1701.07875 · Cited by 2,225
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
Nowozin, S., Cseke, B., & Tomioka, R. (2016) · arXiv · doi:10.48550/arxiv.1606.00709 · Cited by 1,183
A comparison of features for synthetic speech detection
Sahidullah, M., Kinnunen, T., & Hanilçi, C. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-472 · Cited by 382 · cited 1×
“[Identity:] φ(y) = y [Static & delta [52]:] φ(y) = Wy”
The Voice Conversion Challenge 2016
Toda, T., Chen, L.-H., Saito, D., Villavicencio, F., Wester, M., Wu, Z., & Yamagishi, J. (2016) · Interspeech 2016 · doi:10.21437/interspeech.2016-1066 · Cited by 156 · cited 1×
“However, the speech parameters generated from these models tend to be over-smoothed, and the resultant quality of speech is still low compared with that of natural speech [1], [9].”
Background
Research works printed but not linked: 46
- kang, 2014, Statistical parametric speech synthesis using weighted multi-distribution deep belief network, Proc INTERSPEECH, 1959
- 10.1587/transinf.E97.D.1429 · DOI
- 10.1145/2939672.2939778 · DOI · Paper page
- 10.1126/science.1127647 · DOI · Paper page
- 10.1109/ICASSP.2015.7178816 · DOI · Paper page
- glorot, 2011, Deep sparse rectifier neural networks, Proc 14th Int Conf Artif Intell Statist, 315
- reshef, 2011, Detecting novel associations in large data sets, Science, 334, 1518, 10.1126/science.1205438 · DOI · Paper page
- goodfellow, 2017, NIPS 2016 tutorial: Generative adversarial networks
- li, 0, Generative moment matching networks, Proceedings of the 32nd Intl Conf on Machine Learning, 1718
- 10.1007/978-3-540-71050-9 · DOI · Paper page
- 10.1561/0100000004 · DOI · Paper page
- huang, 2015, Multi-task learning deep neural networks for speech feature denoising, Proc INTERSPEECH, 2464
- 10.1109/ICASSP.1988.196677 · DOI
- 10.1016/j.specom.2009.04.004 · DOI · Paper page
- 10.1109/TASL.2010.2076805 · doi:10.1109/tasl.2010.2076805
- 10.1515/9783110197105.515 · DOI · Paper page
- mao, 2017, Least squares generative adversarial networks, IEEE Int Conf Comput Vision (ICCV), 2794
- 10.1162/neco.2007.19.3.780 · DOI · Paper page
- lee, 0, Algorithms for non-negative matrix factorization, Proc Int Conf Neural Inf Process, 556
- takamichi, 2015, The NAIST text-to-speech system for the Blizzard Challenge 2015, Proc Blizzard Challenge Workshop
- toda, 2012, Implementation of computationally efficient real-time voice conversion, Proc INTERSPEECH, 94, 10.21437/Interspeech.2012-34 · doi:10.21437/interspeech.2012-34
- 10.21437/Interspeech.2017-1288 · DOI
- 10.21437/Interspeech.2016-584 · doi:10.21437/interspeech.2016-584
- 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
- 10.1109/TASLP.2016.2522655 · DOI
- 10.1109/ICASSP.2015.7178894 · DOI
- 10.1109/ICASSP.2016.7472749 · doi:10.1109/icassp.2016.7472749
- nose, 2014, Analysis of spectral enhancement using global variance in HMM-based speech synthesis, Proc INTERSPEECH, 2917
- zen, 2013, Statistical parametric speech synthesis using deep neural networks, Proc Int Conf Acoust Speech Signal Process, 7962
- goodfellow, 0, Generative adversarial nets, Proc Int Conf Neural Inf Process, 2672
- 10.1109/TASLP.2016.2526653 · DOI
- chen, 2015, Robust deep feature for spoofing detection the SJTU system for ASVspoof 2015 Challenge, Proc INTERSPEECH, 2097
- 10.1109/MSP.2014.2359987 · DOI · Paper page
- 10.1109/89.661472 · DOI · Paper page
- 10.1109/TASL.2007.907344 · DOI · Paper page
- 10.1109/JPROC.2013.2251852 · DOI · Paper page
- 10.1109/TASLP.2016.2551865 · DOI
- wu, 2006, Minimum generation error training for HMM-based speech synthesis, Proc Int Conf Acoust Speech Signal Process, 89
- 10.1016/S0167-6393(98)00085-5 · DOI · Paper page
- sagisaka, 1990, A large-scale Japanese speech database, Proc Int Conf Spoken Lang Process, 1089
- ohtani, 2006, Maximum likelihood voice conversion based on GMM with STRAIGHT mixed excitation, Proc INTERSPEECH, 2266
- 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
- 10.1109/ICASSP.2017.7953090 · DOI
- 10.1016/j.specom.2015.10.007 · doi:10.1016/j.specom.2015.10.007
- 10.1109/ICASSP.2016.7472757 · DOI
- 10.21437/Interspeech.2016-522 · DOI
Cited by
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3130191 · Cited by 1,231
A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends
Hatcher, W. G., & Yu, W. (2018) · IEEE Access · doi:10.1109/access.2018.2830661 · Cited by 654
“[113] utilized GANs for statistical parametric speech synthesis to alleviate common over-smoothing effects.”
Method“StarGAN-VC: non-parallel many-to-many voice conversion using star generative adversarial networks,”
Kameoka, H., Kaneko, T., Tanaka, K., & Hojo, N. (2018) · 2018 IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2018.8639535 · Cited by 371
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.06937 · Cited by 253
Khanjani, Z., Watson, G., & Janeja, V. P. (2023) · Frontiers in Big Data · doi:10.3389/fdata.2022.1001063 · Cited by 121
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
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.