CycleGAN-VC: Non-parallel Voice Conversion Using Cycle-Consistent Adversarial Networks
The DOI matches its Crossref record; 60 of the 61 references it cites were found in a registry or an index.
Abstract
We propose a non-parallel voice-conversion (VC) method that can learn a mapping from source to target speech without relying on parallel data. The proposed method is particularly noteworthy in that it is general purpose and high quality and works without any extra data, modules, or alignment procedure. Our method, called CycleGAN-VC, uses a cycle-consistent adversarial network (CycleGAN) with gated convolutional neural networks (CNNs) and an identity-mapping loss. A CycleGAN learns forward and inverse mappings simultaneously using adversarial and cycle-consistency losses. This makes it possible to find an optimal pseudo pair from non-parallel data. Furthermore, the adversarial loss can bring the converted speech close to the target one on the basis of indistinguishability without explicit density estimation. This allows to avoid over-smoothing caused by statistical averaging, which occurs in many conventional statistical model-based VC methods that represent data distribution explicitly. We configure a CycleGAN with gated CNNs and train it with an identity-mapping loss. This allows the mapping function to capture sequential and hierarchical structures while preserving linguistic information. We evaluated our method on a non-parallel VC task. An objective evaluation showed that the converted feature sequence was near natural in terms of global variance and modulation spectra, which are structural indicators highly correlated with subjective evaluation. A subjective evaluation showed that the quality of the converted speech was comparable to that obtained with a Gaussian mixture model-based parallel VC method even though CycleGAN-VC is trained under disadvantageous conditions (non-parallel and half the amount of data).
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
“Recent research [59,60,61,62,63] in VC technologies has addressed long-standing challenges such as data scarcity, cross-lingual conversion, and real-time processing.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [59]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“Inspired by a previous study [49] for neural style transfer and super-resolution, we used the network that included downsampling, residual [50], and upsampling layers, as well as incorporating instance normalization [51].”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We trained the network using the Adam optimizer [53] with a batch size of 1.”
MethodFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
Labaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
(2010) · International Conference on Machine Learning · Cited by 13,995
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283 · cited 2×
“Inspired by a previous study [49] for neural style transfer and super-resolution, we used the network that included downsampling, residual [50], and upsampling layers, as well as incorporating instance normalization [51].”
MethodShi, W., Caballero, J., Huszar, F., Totz, J., Aitken, A. P., Bishop, R., Rueckert, D., & Wang, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.207 · Cited by 7,570
“Least squares generative adversarial networks,”
Mao, X., Li, Q., Xie, H., Lau, R. Y. K., Wang, Z., & Smolley, S. P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.304 · Cited by 5,437 · cited 1×
“To stabilize training, we used a least squares GAN [52], which replaces the negative log likelihood objective in Ladv by a least squares loss.”
MethodInstance Normalization: The Missing Ingredient for Fast Stylization
Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.08022 · Cited by 2,775 · cited 1×
“Inspired by a previous study [49] for neural style transfer and super-resolution, we used the network that included downsampling, residual [50], and upsampling layers, as well as incorporating instance normalization [51].”
MethodEmpirical Evaluation of Rectified Activations in Convolutional Network
Xu, B., Wang, N., Chen, T., & Li, M. (2015) · arXiv · doi:10.48550/arxiv.1505.00853 · Cited by 2,264 · cited 1×
“, rectified linear units (ReLUs) [54] for the generator and leaky ReLUs [55], [56] for the discriminator.”
BackgroundDualGAN: Unsupervised Dual Learning for Image-to-Image Translation
Yi, Z., Zhang, H., Tan, P., & Gong, M. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.310 · Cited by 2,134 · cited 2×
“, DiscoGAN [23] or DualGAN [24]) with gated CNNs [25] and an identity-mapping loss [26].”
BackgroundLearning to Discover Cross-Domain Relations with Generative Adversarial Networks
Kim, T., Cha, M., Kim, H., Lee, J. K., & Kim, J. (2017) · arXiv · doi:10.48550/arxiv.1703.05192 · Cited by 1,716 · cited 2×
“, DiscoGAN [23] or DualGAN [24]) with gated CNNs [25] and an identity-mapping loss [26].”
BackgroundJointly Embedding Multiple Single-Cell Omics Measurements
Liu, J., Huang, Y., Singh, R., Vert, J., & Noble, W. S. (2019) · Leibniz international proceedings in informatics · doi:10.4230/lipics.wabi.2019.10 · Cited by 1,141
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 · cited 1×
“The speech data were downsampled to 16 kHz, and 24 Mel-cepstral coefficients (MCEPs), logarithmic fundamental frequency (logF0), and aperiodicities (APs) were then extracted every 5 ms using the WORLD analysis system [45].”
MethodLanguage Modeling with Gated Convolutional Networks
Dauphin, Y., Fan, A., Auli, M., & Grangier, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.08083 · Cited by 1,080 · cited 13×
“To use a CycleGAN for non-parallel VC, we mainly made two modifications to the CycleGAN architecture: gated CNN [25] and identity-mapping loss [26].”
BackgroundMethodInfluentialVoice 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
Continuous probabilistic transform for voice conversion
Stylianou, Y., Cappe, O., & Moulines, E. (1998) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.661472 · Cited by 931 · cited 8×
“ISBN 978-90-827970-1-5 © EURASIP 2018 2100 A subjective evaluation showed that the speech quality was comparable to that obtained with a GMM-based parallel VC method [10] even though CycleGAN-VC is trained under disadvantageous conditions (non-parallel and half the amount of data).”
MethodInfluential(2017) · International Conference on Machine Learning · Cited by 758
Spectral voice conversion for text-to-speech synthesis
Kain, A., & Macon, M. W. (2002) · Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181) · doi:10.1109/icassp.1998.674423 · Cited by 552 · cited 2×
“This technique can be applied to various tasks such as speaker-identity modification for text-to-speech systems [2], speaking assistance [3]–[5], emotion/expressiveness conversion [6], [7], and pronunciation conversion [8].”
MethodUnsupervised Cross-Domain Image Generation
Taigman, Y., Polyak, A., & Wolf, L. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.02200 · Cited by 359 · cited 3×
“To use a CycleGAN for non-parallel VC, we mainly made two modifications to the CycleGAN architecture: gated CNN [25] and identity-mapping loss [26].”
BackgroundMethodLearning Dense Correspondence via 3D-Guided Cycle Consistency
Zhou, T., Krahenbuhl, P., Aubry, M., Huang, Q., & Efros, A. A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.20 · Cited by 350 · cited 2×
“With CycleGAN, a mapping GX→Y is learned using two losses, namely an adversarial loss [27] and cycle-consistency loss [28].”
MethodHsu, 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 · cited 3×
“A few attempts [40]–[43] have recently been made to develop methods that are completely free from parallel data and extra modules, similarly to ours.”
BackgroundMethodVoice conversion from non-parallel corpora using variational auto-encoder
Hsu, C.-C., Hwang, H.-T., Wu, Y.-C., Tsao, Y., & Wang, H.-M. (2016) · 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA) · doi:10.1109/apsipa.2016.7820786 · Cited by 289 · cited 1×
“Following a previous study [41], we used a subset of speakers for evaluation.”
MethodVoice conversion using deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks
Sun, L., Kang, S., Li, K., & Meng, H. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178896 · Cited by 257 · cited 1×
“Neural network (NN)-based methods, such as a restricted Boltzmann machine (RBM) [12], [13], feed forward NN [14]–[16], recurrent NN (RNN) [17], [18], convolutional NN (CNN) [8], and generative adversarial network (GAN) [8], and exemplar-based methods, such as non-negative matrix factorization (NMF) [19], [20], have al…”
MethodSpectral Mapping Using Artificial Neural Networks for Voice Conversion
Desai, S., Black, A. W., Yegnanarayana, B., & Prahallad, K. (2010) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2010.2047683 · Cited by 223 · cited 1×
“Neural network (NN)-based methods, such as a restricted Boltzmann machine (RBM) [12], [13], feed forward NN [14]–[16], recurrent NN (RNN) [17], [18], convolutional NN (CNN) [8], and generative adversarial network (GAN) [8], and exemplar-based methods, such as non-negative matrix factorization (NMF) [19], [20], have al…”
MethodVoice Conversion Using Deep Neural Networks With Layer-Wise Generative Training
Chen, L.-H., Ling, Z.-H., Liu, L.-J., & Dai, L.-R. (2014) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2353991 · Cited by 210 · cited 1×
“Neural network (NN)-based methods, such as a restricted Boltzmann machine (RBM) [12], [13], feed forward NN [14]–[16], recurrent NN (RNN) [17], [18], convolutional NN (CNN) [8], and generative adversarial network (GAN) [8], and exemplar-based methods, such as non-negative matrix factorization (NMF) [19], [20], have al…”
MethodVoice 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 · cited 1×
“One successful approach involves statistical methods using a Gaussian mixture model (GMM) [9]–[11].”
MethodStatistical Voice Conversion Techniques for Body-Conducted Unvoiced Speech Enhancement
Toda, T., Nakagiri, M., & Shikano, K. (2012) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2012.2205241 · Cited by 182 · cited 1×
“This technique can be applied to various tasks such as speaker-identity modification for text-to-speech systems [2], speaking assistance [3]–[5], emotion/expressiveness conversion [6], [7], and pronunciation conversion [8].”
MethodSpeaking-aid systems using GMM-based voice conversion for electrolaryngeal speech
Nakamura, K., Toda, T., Saruwatari, H., & Shikano, K. (2012) · Speech Communication · doi:10.1016/j.specom.2011.07.007 · Cited by 169
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 · cited 1×
“Neural network (NN)-based methods, such as a restricted Boltzmann machine (RBM) [12], [13], feed forward NN [14]–[16], recurrent NN (RNN) [17], [18], convolutional NN (CNN) [8], and generative adversarial network (GAN) [8], and exemplar-based methods, such as non-negative matrix factorization (NMF) [19], [20], have al…”
MethodImproving the intelligibility of dysarthric speech
Kain, A. B., Hosom, J.-P., Niu, X., van Santen, J. P. H., Fried-Oken, M., & Staehely, J. (2007) · Speech Communication · doi:10.1016/j.specom.2007.05.001 · Cited by 158 · cited 1×
“This technique can be applied to various tasks such as speaker-identity modification for text-to-speech systems [2], speaking assistance [3]–[5], emotion/expressiveness conversion [6], [7], and pronunciation conversion [8].”
MethodParallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks
Kaneko, T., & Kameoka, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.11293 · Cited by 158
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 · cited 2×
“We evaluated our method on a non-parallel VC task using the VCC 2016 dataset [32], which was recorded by professional US English speakers, including five females and five males.”
MethodGenerative adversarial network-based postfilter for statistical parametric speech synthesis
Kaneko, T., Kameoka, H., Hojo, N., Ijima, Y., Hiramatsu, K., & Kashino, K. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953090 · Cited by 146 · cited 4×
“Implementation details: We designed a network based on the recent success in image modeling [22], [48], [49] and speech modeling [8], [29].”
BackgroundMethodSelf-citationKaneko, T., Kameoka, H., Hiramatsu, K., & Kashino, K. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-970 · Cited by 127
Self-citationEigenvoice conversion based on Gaussian mixture model
Toda, T., Ohtani, Y., & Shikano, K. (2006) · Interspeech (USB) · doi:10.21437/interspeech.2006-613 · Cited by 113 · cited 1×
“Other approaches involve methods using an adaptation technique [36], [37] or incorporating a pre-constructed speaker space [38], [39].”
MethodMaximum likelihood voice conversion based on GMM with STRAIGHT mixed excitation
Ohtani, Y., Toda, T., Saruwatari, H., & Shikano, K. (2006) · Interspeech (USB) · doi:10.21437/interspeech.2006-582 · Cited by 101 · cited 1×
“Aperiodicities were directly used without modification because a previous study [47] showed that converting APs does not significantly affect speech quality.”
MethodNonparallel training for voice conversion based on a parameter adaptation approach
Mouchtaris, A., der Spiegel, J. V., & Müeller, P. (2006) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tsa.2005.857790 · Cited by 101 · cited 1×
“Other approaches involve methods using an adaptation technique [36], [37] or incorporating a pre-constructed speaker space [38], [39].”
MethodMap-based adaptation for speech conversion using adaptation data selection and non-parallel training
Lee, C.-H., & Wu, C. (2006) · Interspeech (USB) · doi:10.21437/interspeech.2006-579 · Cited by 97 · cited 1×
“Other approaches involve methods using an adaptation technique [36], [37] or incorporating a pre-constructed speaker space [38], [39].”
MethodVoice conversion using deep neural networks with speaker-independent pre-training
Mohammadi, S. H., & Kain, A. (2014) · 2014 IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2014.7078543 · Cited by 94
One-to-many voice conversion based on tensor representation of speaker space
Saito, D., Yamamoto, K., Minematsu, N., & Hirose, K. (2011) · Interspeech (USB) · doi:10.21437/interspeech.2011-268 · Cited by 86 · cited 1×
“Other approaches involve methods using an adaptation technique [36], [37] or incorporating a pre-constructed speaker space [38], [39].”
MethodData-driven emotion conversion in spoken English
Inanoglu, Z., & Young, S. J. (2008) · Speech Communication · doi:10.1016/j.specom.2008.09.006 · Cited by 79 · cited 1×
“This technique can be applied to various tasks such as speaker-identity modification for text-to-speech systems [2], speaking assistance [3]–[5], emotion/expressiveness conversion [6], [7], and pronunciation conversion [8].”
MethodLiu, K., Zhang, J., & Yan, Y. (2007) · International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) · doi:10.1109/fskd.2007.347 · Cited by 68 · cited 1×
“The F0 was converted using logarithm Gaussian normalized transformation [46].”
MethodA KL Divergence and DNN-Based Approach to Voice Conversion without Parallel Training Sentences
Xie, F., Soong, F. K., & Li, H. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-116 · Cited by 66 · cited 1×
“One approach involves using an ASR module to find a pair of corresponding frames [34], [35].”
BackgroundGenerative Adversarial Network-Based Postfilter for STFT Spectrograms
Kaneko, T., Takaki, S., Kameoka, H., & Yamagishi, J. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-962 · Cited by 65 · cited 1×
“To fill the margin, we plan to apply our method to other features, such as STFT spectrograms [30], and other speech-synthesis frameworks, such as vocoder-free VC [58].”
MethodSelf-citationKinnunen, T., Juvela, L., Alku, P., & Yamagishi, J. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953215 · Cited by 63
Analysis of the Voice Conversion Challenge 2016 Evaluation Results
Wester, M., Wu, Z., & Yamagishi, J. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-1331 · Cited by 61 · cited 2×
“By referring to the VCC 2016 [57], we evaluated the naturalness and speaker similarity of the converted samples.”
MethodNon-Parallel Training in Voice Conversion Using an Adaptive Restricted Boltzmann Machine
Nakashika, T., Takiguchi, T., & Minami, Y. (2016) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2016.2593263 · Cited by 59 · cited 1×
“A few attempts [40]–[43] have recently been made to develop methods that are completely free from parallel data and extra modules, similarly to ours.”
MethodEvaluation of Expressive Speech Synthesis With Voice Conversion and Copy Resynthesis Techniques
Türk, O., & Schroder, M. (2010) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2010.2041113 · Cited by 56 · cited 1×
“This technique can be applied to various tasks such as speaker-identity modification for text-to-speech systems [2], speaking assistance [3]–[5], emotion/expressiveness conversion [6], [7], and pronunciation conversion [8].”
MethodNakashika, T., Takiguchi, T., & Ariki, Y. (2014) · Interspeech (USB) · doi:10.21437/interspeech.2014-447 · Cited by 54 · cited 2×
“An effective way to represent such structures would be to use an RNN, but it is computationally demanding due to the difficulty of parallel implementations.”
MethodA postfilter to modify the modulation spectrum in HMM-based speech synthesis
Takamichi, S., Toda, T., Neubig, G., Sakti, S., & Nakamura, S. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6853604 · Cited by 52 · cited 2×
“Therefore, as alternatives, we used two structural indicators highly correlated with subjective evaluation: GV [10] and MS [33].”
BackgroundMethodOn the impact of alignment on voice conversion performance
Helander, E., Schwarz, J., Nurminen, J., Silen, H., & Gabbouj, M. (2008) · Interspeech 2008 · doi:10.21437/interspeech.2008-419 · Cited by 42 · cited 1×
“This can be problematic since misalignment involved in parallel data can cause speech-quality degradation; thus, careful pre-screening and manual correction may be required [21].”
BackgroundVoice Conversion Based on Speaker-Dependent Restricted Boltzmann Machines
Nakashika, T., Takiguchi, T., & Ariki, Y. (2014) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e97.d.1403 · Cited by 40 · cited 1×
“Neural network (NN)-based methods, such as a restricted Boltzmann machine (RBM) [12], [13], feed forward NN [14]–[16], recurrent NN (RNN) [17], [18], convolutional NN (CNN) [8], and generative adversarial network (GAN) [8], and exemplar-based methods, such as non-negative matrix factorization (NMF) [19], [20], have al…”
MethodExemplar-Based Voice Conversion Using Sparse Representation in Noisy Environments
Takashima, R., Takiguchi, T., & Ariki, Y. (2013) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.e96.a.1946 · Cited by 38 · cited 1×
“Neural network (NN)-based methods, such as a restricted Boltzmann machine (RBM) [12], [13], feed forward NN [14]–[16], recurrent NN (RNN) [17], [18], convolutional NN (CNN) [8], and generative adversarial network (GAN) [8], and exemplar-based methods, such as non-negative matrix factorization (NMF) [19], [20], have al…”
MethodText-independent voice conversion based on state mapped codebook
Zhang, M., Tao, J., Tian, J., & Wang, X. (2008) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2008.4518682 · Cited by 33 · cited 1×
“One approach involves using an ASR module to find a pair of corresponding frames [34], [35].”
BackgroundTraining algorithm to deceive Anti-Spoofing Verification for DNN-based speech synthesis
Saito, Y., Takamichi, S., & Saruwatari, H. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953088 · Cited by 24 · cited 1×
“This allows to avoid oversmoothing caused by statistical averaging [8], [16], [29]–[31], which occurs in many conventional statistical model-based VC methods that represent data distribution explicitly (e.”
MethodOyamada, K., Kameoka, H., Kaneko, T., Ando, H., Hiramatsu, K., & Kashino, K. (2017) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2017.8282025 · Cited by 20 · cited 2×
“This allows to avoid oversmoothing caused by statistical averaging [8], [16], [29]–[31], which occurs in many conventional statistical model-based VC methods that represent data distribution explicitly (e.”
MethodSelf-citationKobayashi, K., Toda, T., & Nakamura, S. (2016) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2016.7846338 · Cited by 16 · cited 1×
“To fill the margin, we plan to apply our method to other features, such as STFT spectrograms [30], and other speech-synthesis frameworks, such as vocoder-free VC [58].”
Method
Research works printed but not linked: 1
- maas, 2013, Rectifier nonlinearities improve neural network acoustic models, Proc ICML Workshop
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
Masood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023) · Applied Intelligence · doi:10.1007/s10489-022-03766-z · Cited by 543
“Recent GAN-based approaches, such as CycleGAN [253–256], VAW-GAN [257], and StarGAN [258], attempt to achieve high-quality transformed speech using non-parallel training data.”
MethodAn 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
“Combining these three loss functions, we can obtain the overall loss function of CycleGAN [48], [210].”
BackgroundMethodCycleGAN-VC2: improved CycleGAN-based non-parallel voice conversion.
Kaneko, T., Kameoka, H., Tanaka, K., & Hojo, N. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8682897 · Cited by 272
Self-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
Metadata
- Authors
- Kaneko, T., & Kameoka, H.
- Affiliations
- NTT (Japan) (JP)
- Venue
- 2018 26th European Signal Processing Conference (EUSIPCO)
- Publisher
- IEEE
- Published
- 2018-09
- Pages
- 2100-2104
- OpenAlex
- W2902070858
- Cited by
- 358
- References
- 61
- Citations by year
- 2026: 19 · 2025: 36 · 2024: 50 · 2023: 66 · 2022: 58 · 2021: 63 · 2020: 47 · 2019: 18 · 2018: 1
- FWCI
- 13.16
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- European Signal Processing Conference (EUSIPCO) (publishedVersion)
- 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, non-parallel voice conversion, CycleGAN, gated convolutional neural network, pseudo data generation, over-smoothing, modulation spectra
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.