Group Sparse Representation With WaveNet Vocoder Adaptation for Spectrum and Prosody Conversion
The DOI matches its Crossref record; 68 of the 76 references it cites were found in a registry or an index.
Abstract
The statistical approach to voice conversion typically consists of a feature conversion module followed by a vocoder. So far, the feature conversion studies are mainly focused on the conversion of spectrum. However, speaker identity is also characterized by prosodic features, such as fundamental frequency F0 and energy contour among others. In this paper, we study the transformation of speaker characteristics both in terms of spectrum and prosody. We propose two novel techniques that effectively use a limited amount of source-target training data and leverage a large general speech corpus to improve the voice conversion quality. First, we study the phonetic sparse representation under the group sparsity mathematical formulation. We use phonetic posteriorgrams PPGs together with spectral and prosody features to form tandem feature in the phonetic dictionary. The tandem feature allow us to estimate an activation matrix that is less dependent on source speakers, thus providing a better voice conversion quality. Second, we study the use of WaveNet vocoder that can be trained on general speech corpus from multiple speakers and adapted on target speaker data to improve the vocoding quality. We benefit from the large general speech databases that are used to train the PPG generator, and the WaveNet vocoder. The experiments show that the proposed conversion framework outperforms the traditional spectrum and prosody conversion techniques in both objective and subjective evaluations.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Benefiting from advancements in neural vocoders, modern VC systems have redefined their architecture. Since a neural vocoder itself is trainable, it enables joint training with conversion models [57] and, in some cases, speech analysis modules [58], achieving an E2E structure.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [58]
Citations
Cites
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
ALGORITHMS FOR NON-NEGATIVE MATRIX FACTORIZATION
Lee, D. D., & Seung, H. S. (2000) · neural information processing systems · Cited by 9,968
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
Kaldi Speech Recognition Toolkit
Povey, D. (2024) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.57702/jb3fvbn9 · Cited by 4,609
Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions
Shen, J., Pang, R., Weiss, R. J., Schuster, M., Jaitly, N., Yang, Z., Chen, Z., Zhang, Y., Wang, Y., Skerrv-Ryan, R., et al. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461368 · Cited by 2,791
Ladd, D. R. (1996) · Cited by 2,742
WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications
MORISE, M., YOKOMORI, F., & OZAWA, K. (2016) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2015edp7457 · Cited by 1,092
Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory
Toda, T., Black, A. W., & Tokuda, K. (2007) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/tasl.2007.907344 · Cited by 937
Mel-cepstral distance measure for objective speech quality assessment
Kubichek, R. (2002) · Proceedings of IEEE Pacific Rim Conference on Communications Computers and Signal Processing · doi:10.1109/pacrim.1993.407206 · Cited by 534
Taylor, P. (2009) · Cambridge University Press eBooks · doi:10.1017/cbo9780511816338 · Cited by 529
Voice conversion through vector quantization
Abe, M., Nakamura, S., Shikano, K., & Kuwabara, H. (2003) · ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1988.196671 · Cited by 415
Speech Synthesis Based on Hidden Markov Models
Tokuda, K., Nankaku, Y., Toda, T., Zen, H., Yamagishi, J., & Oura, K. (2013) · Proceedings of the IEEE · doi:10.1109/jproc.2013.2251852 · Cited by 404
Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization
Mohammadiha, N., Smaragdis, P., & Leijon, A. (2013) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2013.2270369 · Cited by 389
“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
Hsu, C.-C., Hwang, H.-T., Wu, Y.-C., Tsao, Y., & Wang, H.-M. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-63 · Cited by 320
Phonetic posteriorgrams for many-to-one voice conversion without parallel data training
Sun, L., Li, K., Wang, H., Kang, S., & Meng, H. (2016) · 2016 IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2016.7552917 · Cited by 297
Query-by-example spoken term detection using phonetic posteriorgram templates
Hazen, T. J., Shen, W., & White, C. (2009) · 2009 IEEE Workshop on Automatic Speech Recognition & Understanding · doi:10.1109/asru.2009.5372889 · Cited by 275
Speech denoising using nonnegative matrix factorization with priors
Wilson, K. W., Raj, B., Smaragdis, P., & Divakaran, A. (2008) · 2008 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2008.4518538 · Cited by 273
Speaker-Dependent WaveNet Vocoder
Tamamori, A., Hayashi, T., Kobayashi, K., Takeda, K., & Toda, T. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-314 · Cited by 269
The music of everyday speech: prosody and discourse analysis
(2002) · Choice Reviews Online · doi:10.5860/choice.39-5642 · Cited by 217
Voice Conversion Using Partial Least Squares Regression
Helander, E., Virtanen, T., Nurminen, J., & Gabbouj, M. (2010) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2010.2041699 · Cited by 207
Exemplar-Based Sparse Representation With Residual Compensation for Voice Conversion
Wu, Z., Virtanen, T., Chng, E. S., & Li, H. (2014) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2333242 · Cited by 166
Self-citationThe 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
Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
Hsu, W.-N., Zhang, Y., & Glass, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.07902 · Cited by 148
Learning Latent Representations for Speech Generation and Transformation
Hsu, W.-N., Zhang, Y., & Glass, J. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-349 · Cited by 141
Voice Conversion Using Dynamic Kernel Partial Least Squares Regression
Helander, E., Silen, H., Virtanen, T., & Gabbouj, M. (2012) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2011.2165944 · Cited by 126
Exemplar-based voice conversion in noisy environment
Takashima, R., Takiguchi, T., & Ariki, Y. (2012) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2012.6424242 · Cited by 122
Sun, M., Li, Y., Gemmeke, J. F., & Zhang, X. (2015) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2015.2427520 · Cited by 98
An investigation of multi-speaker training for wavenet vocoder
Hayashi, T., Tamamori, A., Kobayashi, K., Takeda, K., & Toda, T. (2017) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2017.8269007 · Cited by 97
Deep Bidirectional LSTM Modeling of Timbre and Prosody for Emotional Voice Conversion
Ming, H., Huang, D., Xie, L., Wu, J., Dong, M., & Li, H. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-1053 · Cited by 94
Self-citationOne-to-Many and Many-to-One Voice Conversion Based on Eigenvoices
Toda, T., Ohtani, Y., & Shikano, K. (2007) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2007.367303 · Cited by 89
Statistical Voice Conversion with WaveNet-Based Waveform Generation
Kobayashi, K., Hayashi, T., Tamamori, A., & Toda, T. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-986 · Cited by 80
Group Sparsity in Nonnegative Matrix Factorization
Kim, J., Monteiro, R. D. C., & Park, H. (2012) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611972825.73 · Cited by 78
Personalized, Cross-Lingual TTS Using Phonetic Posteriorgrams
Sun, L., Wang, H., Kang, S., Li, K., & Meng, H. M. L. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-1043 · Cited by 72
Ohala, J. J., Dunn, A. L., & Sprouse, R. (2004) · Speech prosody · doi:10.21437/speechprosody.2004-38 · Cited by 66
Multilevel parametric-base F0 model for speech synthesis
Latorre, J., & Akamine, M. (2008) · Interspeech (USB) · doi:10.21437/interspeech.2008-558 · Cited by 65
Speaker adaptation and voice conversion by codebook mapping
Shikano, K., Nakamura, S., & Abe, M. (1991) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.1991.176405 · Cited by 54
Wavelets for intonation modeling in HMM speech synthesis
Suni, A., Aalto, D., Raitio, T., Alku, P., & Vainio, M. (2013) · Työväentutkimus Vuosikirja · Cited by 47
Exemplar-based sparse representation of timbre and prosody for voice conversion
Ming, H., Huang, D., Xie, L., Zhang, S., Dong, M., & Li, H. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472664 · Cited by 41
Self-citationKameoka, H., Kaneko, T., Tanaka, K., & Hojo, N. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.05092 · Cited by 40
Voice conversion based on Non-negative matrix factorization using phoneme-categorized dictionary
Aihara, R., Nakashika, T., Takiguchi, T., & Ariki, Y. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6855137 · Cited by 39
Fundamental frequency modeling using wavelets for emotional voice conversion
Ming, H., Huang, D., Dong, M., Li, H., Xie, L., & Zhang, S. (2015) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii.2015.7344665 · Cited by 39
Self-citationEmotional voice conversion using neural networks with arbitrary scales F0 based on wavelet transform
Luo, Z., Chen, J., Takiguchi, T., & Ariki, Y. (2017) · EURASIP Journal on Audio Speech and Music Processing · doi:10.1186/s13636-017-0116-2 · Cited by 39
Sparse representation of phonetic features for voice conversion with and without parallel data
Şişman, B., Li, H., & Tan, K. C. (2017) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2017.8269002 · Cited by 39
Self-citationGillett, B., & King, S. (2003) · 8th European Conference on Speech Communication and Technology (Eurospeech 2003) · doi:10.21437/eurospeech.2003-74 · Cited by 37
Ribeiro, M. S., & Clark, R. A. J. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178904 · Cited by 37
Text-independent F0 transformation with non-parallel data for voice conversion
Wu, Z., Kinnunen, T., Chng, E. S., & Li, H. (2010) · Interspeech (USB) · doi:10.21437/interspeech.2010-497 · Cited by 36
Self-citationEvent selection from phone posteriorgrams using matched filters
Kintzley, K., Jansen, A., & Heřmanský, H. (2011) · Interspeech (USB) · doi:10.21437/interspeech.2011-354 · Cited by 34
Continuous wavelet transform for analysis of speech prosody
Vainio, M., Suni, A., & Aalto, D. (2013) · Työväentutkimus Vuosikirja · Cited by 34
Wavelet Analysis of Speaker Dependent and Independent Prosody for Voice Conversion
Şişman, B., & Li, H. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-1499 · Cited by 31
Self-citationLocally Linear Embedding for Exemplar-Based Spectral Conversion
Wu, Y.-C., Hwang, H.-T., Hsu, C.-C., Tsao, Y., & Wang, H. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-567 · Cited by 30
Cute: A concatenative method for voice conversion using exemplar-based unit selection
Jin, Z., Finkelstein, A., DiVerdi, S., Lu, J., & Mysore, G. J. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472761 · Cited by 29
Transformation of prosody in voice conversion
Şişman, B., Li, H., & Tan, K. C. (2017) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2017.8282288 · Cited by 28
Self-citationGroup sparsity for speaker identity discrimination in factorisation-based speech recognition
Hurmalainen, A., Saeidi, R., & Virtanen, T. I. (2012) · Interspeech (USB) · doi:10.21437/interspeech.2012-571 · Cited by 26
Wavelet Speech Enhancement Based on Nonnegative Matrix Factorization
Wang, S., Chern, A., Tsao, Y., Hung, J.-W., Lu, X., Lai, Y.-H., & Su, B. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2571727 · Cited by 26
Luo, Z., Chen, J., Takiguchi, T., & Ariki, Y. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-984 · Cited by 26
Hierarchical modeling of F0 contours for voice conversion
Sánchez, G., Silén, H., Nurminen, J., & Gabbouj, M. (2014) · Interspeech (USB) · doi:10.21437/interspeech.2014-189 · Cited by 24
SPEECH PROSODY: A METHODOLOGICAL REVIEW
Xu, & ̆, Y. (2011) · Cited by 21
The NU-NAIST Voice Conversion System for the Voice Conversion Challenge 2016
Kobayashi, K., Takamichi, S., Nakamura, S., & Toda, T. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-970 · Cited by 20
Activity-mapping non-negative matrix factorization for exemplar-based voice conversion
Aihara, R., Takiguchi, T., & Ariki, Y. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178902 · Cited by 15
Semi-supervised noise dictionary adaptation for exemplar-based noise robust speech recognition
Luan, Y., Saito, D., Kashiwagi, Y., Minematsu, N., & Hirose, K. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6853897 · Cited by 15
Probabilistic feature mapping based on trajectory HMMs
Zen, H., Nankaku, Y., & Tokuda, K. (2008) · Interspeech (USB) · doi:10.21437/interspeech.2008-330 · Cited by 13
Serizel, R., Essid, S., & Gaël Richard, A. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472723 · Cited by 9
Speech enhancement using non negative matrix factorization and enhanced NMF
Akarsh, K. A., & Selvi, R. S. (2015) · International Conference on Circuits, Power and Computing Technologies (ICCPCT) · doi:10.1109/iccpct.2015.7159386 · Cited by 8
Parallel Dictionary Learning for Multimodal Voice Conversion Using Matrix Factorization
Aihara, R., Masaka, K., Takiguchi, T., & Ariki, Y. (2016) · Studies in computational intelligence · doi:10.1007/978-3-319-40171-3_3 · Cited by 8
Phonetically Aware Exemplar-Based Prosody Transformation
Şişman, B., Lee, G., & Li, H. (2018) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2018-38 · Cited by 8
Self-citationDictionary update for NMF-based voice conversion using an encoder-decoder network
Hsu, C.-C., Hwang, H.-T., Wu, Y.-C., Tsao, Y., & Wang, H. (2016) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.1109/iscslp.2016.7918382 · Cited by 4
A style capturing approach to F0 transformation in voice conversion
Anumanchipalli, G. K., Oliveira, L., & Black, A. W. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6639002 · Cited by 2
Research works printed but not linked: 4
- lifa, 0, Phonetic posteriorgrams for many-to-one voice conversion without parallel data training, Proc IEEE Int Conf Multimedia Expo, 1
- bolinger, 1962, Intonation as a universal, Int COngr Linguists Cambridge
- furui, 2000, Digital speech processing, synthesis, and recognition(revised and expanded), Digital Speech Processing Synthesis and Recognition
- wu, 0, Examplar-based voice conversion using non-negative spectrogram deconvolution, Proc ISCA Speech Synthesis Workshop
Cited by
An Overview of Voice Conversion and Its Challenges: From Statistical Modeling to Deep Learning
Sisman, B., Yamagishi, J., King, S., & Li, H. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2020.3038524 · Cited by 357
“The common objective evaluation metrics include Mel-cepstral distortion (MCD) [246] for spectrum, and PCC [247] and RMSE [248]–[250] for prosody.”
BackgroundMethodResultInfluentialSelf-citationSeen and Unseen Emotional Style Transfer for Voice Conversion with A New Emotional Speech Dataset
Zhou, K., Sisman, B., Liu, R., & Li, H. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9413391 · Cited by 190
“Traditional VC research includes modelling spectral mapping with statistical methods such as Gaussian mixture model (GMM) [5], partial least square regression [6] and sparse representation [7].”
MethodSelf-citationEmotional voice conversion: Theory, databases and ESD
Zhou, K., Sisman, B., Liu, R., & Li, H. (2022) · Speech Communication · doi:10.1016/j.specom.2021.11.006 · Cited by 181
Self-citationExpressive TTS Training With Frame and Style Reconstruction Loss
Liu, R., Şişman, B., Gao, G., & Li, H. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3076369 · Cited by 96
Self-citationTransforming Spectrum and Prosody for Emotional Voice Conversion with Non-Parallel Training Data
Zhou, K., Şişman, B., & Li, H. (2020) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2020-33 · Cited by 93
Self-citation
Metadata
- Authors
- Sisman, B., Zhang, M., & Li, H.
- Affiliations
- National University of Singapore (SG)
- Venue
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Published
- 2019-06
- Volume
- 27
- Issue
- 6
- Pages
- 1085-1097
- ISSN
- 2329-9290 (ISSN-L)
- 2329-9304
- OpenAlex
- W2941094131
- Cited by
- 52
- References
- 76
- Citations by year
- 2026: 1 · 2025: 2 · 2024: 4 · 2023: 3 · 2022: 3 · 2021: 15 · 2020: 17 · 2019: 7
- FWCI
- 4.85
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE/ACM Transactions on Audio Speech and Language Processing (publishedVersion)
- Funders
- Ministry of Education, Singapore AcRF Tier1 NUS Start-up (FY2016)
- SINGA Scholarship under A*STAR Graduate Academy
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Keywords
- voice conversion, group sparse representation, spectrum conversion, phonetic posteriorgrams, phonetic dictionary, fundamental frequency, energy contour, limited training data
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.