The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
The Voice Conversion Challenge 2016
Open accessAbstract
This paper describes the Voice Conversion Challenge 2016 devised by the authors to better understand different voice conversion (VC) techniques by comparing their performance on a common dataset. The task of the challenge was speaker conversion, i.e., to transform the voice identity of a source speaker into that of a target speaker while preserving the linguistic content. Using a common dataset consisting of 162 utterances for training and 54 utterances for evaluation from each of 5 source and 5 target speakers, 17 groups working in VC around the world developed their own VC systems for every combination of the source and target speakers, i.e., 25 systems in total, and generated voice samples converted by the developed systems. These samples were evaluated in terms of target speaker similarity and naturalness by 200 listeners in a controlled environment. This paper summarizes the design of the challenge, its result, and a future plan to share views about unsolved problems and challenges faced by the current VC techniques.
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
“A benefit of using voice conversion is it can help those with speech disorders, which is useful for rehabilitation medicine (Abe et al., 1990; Toda et al., 2016).”
From Audio deepfakes: A survey (2023) · cites this paper as Toda et al., 2016
In the citing paper
“Voice conversion challenge 2016 database (Toda et al., 2016): The original dataset created by the challenge organisers was derived from the DAPS (Device and Produced Speech) Dataset (Mysore, 2015). It contains 216 utterances (162 for training and 54 for testing) per speaker from 10 speakers.”
From Deepfake: definitions, performance metrics and standards, datasets, and a meta-review (2024) · cites this paper as Toda et al., 2016
Citations
Cites
Kawahara, H., Masuda-Katsuse, I., & de Cheveigné, A. (1999) · Speech Communication · doi:10.1016/s0167-6393(98)00085-5 · Cited by 1,831 · cited 1×
“Various sophisticated techniques, such as harmonic plus noise model (HNM) [15] and STRAIGHT [16], have been often used to extract high quality speech features from a speech waveform, and also to generate a speech wave-form from the converted speech features.”
MethodVoice 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
Self-citationContinuous 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
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 · cited 1×
“VC research has a relatively long history from the late 1980s onwards [11].”
BackgroundApplying the harmonic plus noise model in concatenative speech synthesis
Stylianou, Y. (2001) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.890068 · Cited by 325
Voice 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
Mel-generalized cepstral analysis - a unified approach to speech spectral estimation
Tokuda, K., Kobayashi, T., Masuko, T., & Imai, S. (1994) · 3rd International Conference on Spoken Language Processing (ICSLP 1994) · doi:10.21437/icslp.1994-275 · Cited by 237
Spectral 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
Voice 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
Self-citationStatistical 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
Self-citation
Cited by
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
“Various VC challenges (VCC) have been held to encourage the development of VC techniques and improve the quality of converted speech [198-200].”
BackgroundMethodInfluentialAn 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
“conversion challenge (VCC) 2016, which was first launched [67]–[69] at INTERSPEECH 2016.”
BackgroundMethodInfluentialSelf-citationCycleGAN-VC: Non-parallel Voice Conversion Using Cycle-Consistent Adversarial Networks
Kaneko, T., & Kameoka, H. (2018) · 2018 26th European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2018.8553236 · Cited by 358
“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.”
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
“The proposed VC system was evaluated on the Voice Conversion Challenge 2016 dataset [8].”
MethodThe Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods
Lorenzo-Trueba, J., Yamagishi, J., Toda, T., Saito, D., Villavicencio, F., Kinnunen, T., & Ling, Z. (2018) · The Speaker and Language Recognition Workshop (Odyssey 2018) · doi:10.21437/odyssey.2018-28 · Cited by 305
Self-citationVoice 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
“1) The VCC2016 Speech Corpus: The proposed SC system was evaluated on a parallel English corpus from the Voice Conversion Challenge 2016 [20].”
MethodAn overview of voice conversion systems
Mohammadi, S. H., & Kain, A. (2017) · Speech Communication · doi:10.1016/j.specom.2017.01.008 · Cited by 264
Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks
Saito, Y., Takamichi, S., & Saruwatari, H. (2018) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2017.2761547 · Cited by 223
“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].”
BackgroundGeneralization Ability of MOS Prediction Networks
Cooper, E., Huang, W.-C., Toda, T., & Yamagishi, J. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746395 · Cited by 230
“The Blizzard Challenges that we included were [8, 9, 10, 11, 12, 13], as well as all Voice Conversion Challenge years [14, 15, 16, 17, 18].”
Self-citationDeepfake: definitions, performance metrics and standards, datasets, and a meta-review
Altuncu, E., Franqueira, V. N. L., & Li, S. (2024) · Frontiers in Big Data · doi:10.3389/fdata.2024.1400024 · Cited by 134
“Voice Conversion Challenge 2016 database [62]: The original dataset created by the challenge organisers was derived from the DAPS (Device and Produced Speech) Dataset [47].”
MethodDeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices
Wang, R., Juefei-Xu, F., Huang, Y., Guo, Q., Xie, X., Ma, L., & Liu, Y. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413716 · Cited by 131
“entity into the target speaker. Sprocket also served as a baseline system in voice conversion challenge 2018 (VCC18) [25]. Here, real voices are collected from voice conversion challenge 2016 (VCC16) [53] and VCC18. The second dataset is called Sprocket-VC. However, fake voices in the first and second datasets are all…”
BackgroundVoice Conversion Challenge 2020 –- Intra-lingual semi-parallel and cross-lingual voice conversion –-
Yi, Z., Huang, W.-C., Tian, X., Yamagishi, J., Das, R. K., Kinnunen, T., Ling, Z.-H., & Toda, T. (2020) · Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020 · doi:10.21437/vcc_bc.2020-14 · Cited by 126
Self-citationKhanjani, Z., Watson, G., & Janeja, V. P. (2023) · Frontiers in Big Data · doi:10.3389/fdata.2022.1001063 · Cited by 121
“A benefit of using voice conversion is it can help those with speech disorders, which is useful for rehabilitation medicine (Abe et al., 1990; Toda et al., 2016).”
BackgroundMethodMBNET: MOS Prediction for Synthesized Speech with Mean-Bias Network
Leng, Y., Tan, X., Zhao, S., Soong, F. K., Li, X., & Qin, T. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413877 · Cited by 140
“In order to test the generalization ability of MBNet, we further utilize the MOS dataset from Voice Conversion Challenge 2016 (VCC 2016) [20] including 26028 audios from 20 systems as the test set.”
MethodReversing the irreversible: A survey on inverse biometrics
Gomez‐Barrero, M., & Javier Galbally, A. (2019) · Computers & Security · doi:10.1016/j.cose.2019.101700 · Cited by 108
“Numerous e ff orts have been directed towards this research field within the speaker recognition community [70], stemming from the initial proposals from the late 80’s and early 90’s [71, 72] and leading to the very recent Voice Conversion Challenge 2016 [73].”
BackgroundIntroduction to Voice Presentation Attack Detection and Recent Advances
Sahidullah, M., Delgado, H., Todisco, M., Kinnunen, T., Evans, N., Yamagishi, J., & Lee, K. A. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-92627-8_15 · Cited by 73
Self-citationCross-lingual Voice Conversion with Bilingual Phonetic Posteriorgram and Average Modeling
Zhou, Y., Tian, X., Xu, H., Das, R. K., & Li, H. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683746 · Cited by 86
“We chose 10 English speakers (5 male and 5 female) from VCC2016 database [28] and 10 Mandarin speakers (5 male and 5 female) from a Mandarin average model database 1 for average model training.”
MethodDeep Learning Based Assessment of Synthetic Speech Naturalness
Mittag, G., & Möller, S. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2382 · Cited by 108
“The authors would like to thank the organizers of the Blizzard Challenge and the Voice Conversion Challenge for making the results of past challenges available.”
BackgroundInfluentialAnalysis 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
“Q indicate the 17 participants [1] and S = source, T = target and B = baseline.”
InfluentialSelf-citationLDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech
Huang, W.-C., Cooper, E., Yamagishi, J., & Toda, T. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747222 · Cited by 109
Self-citationCDPAM: Contrastive Learning for Perceptual Audio Similarity
Manocha, P., Jin, Z., Zhang, R., & Finkelstein, A. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413711 · Cited by 100
Utilizing Self-Supervised Representations for MOS Prediction
Tseng, W.-C., Huang, C., Kao, W.-T., Lin, Y. Y., & Lee, H.-Y. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-2013 · Cited by 75
Group sparse representation with wavenet vocoder adaptation for spectrum and prosody conversion
Sisman, B., Zhang, M., & Li, H. (2019) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2019.2910637 · Cited by 52
Das, R. K., Kinnunen, T., Huang, W.-C., Ling, Z.-H., Yamagishi, J., Yi, Z., Tian, X., & Toda, T. (2020) · doi:10.21437/vcc_bc.2020-15 · Cited by 64
Self-citationThe Singing Voice Conversion Challenge 2023
Huang, W.-C., Violeta, L. P., Liu, S., Shi, J., & Toda, T. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389671 · Cited by 97
“In light of this, the Voice Conversion Challenge (VCC) was first launched in 2016 [8], followed by there precedent versions in 2018 [9] and 2020 [10].”
BackgroundSelf-citationHow do Voices from Past Speech Synthesis Challenges Compare Today?
Cooper, E., & Yamagishi, J. (2021) · ISCA Speech Synthesis Workshop (SSW) · doi:10.21437/ssw.2021-32 · Cited by 109
Self-citationVoice Mimicry Attacks Assisted by Automatic Speaker Verification
Vestman, V., Kinnunen, T., Hautamäki, R. G., & Sahidullah, M. (2019) · Computer Speech & Language · doi:10.1016/j.csl.2019.05.005 · Cited by 49
“The speech synthesis community has independently launched voice conversion challenges [7, 8] to advance VC methods (though targeted primarily for human listeners rather than for ASV spoofing).”
Pretraining Techniques for Sequence-to-Sequence Voice Conversion
Huang, W.-C., Hayashi, T., Wu, Y.-C., Kameoka, H., & Toda, T. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3049336 · Cited by 57
“In VC, it is common to limit the size of training data to around 5 or 10 minutes [31], [32], wherein existing seq2seq VC literature, approximately 1 h of data is usually used.”
Self-citationSparse 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
“We conducted the experiments using VCC 2016 database [38, 39] to assess the performance of the proposed Phonetic Sparse Representation framework with and without parallel training data.”
MethodXue, Y., Hamada, Y., & Akagi, M. (2018) · Speech Communication · doi:10.1016/j.specom.2018.06.006 · Cited by 38
Wubet, Y. A., & Lian, K. (2022) · IEEE Access · doi:10.1109/access.2022.3200479 · Cited by 47
“Three VC challenges [18], [19], [20] have been addressed to date.”
BackgroundA review on subjective and objective evaluation of synthetic speech
Cooper, E., Huang, W.-C., Tsao, Y., Wang, H., Toda, T., & Yamagishi, J. (2024) · Nippon Onkyo Gakkaishi/Acoustical science and technology/Nihon Onkyo Gakkaishi · doi:10.1250/ast.e24.12 · Cited by 75
Self-citationConditional End-to-End Audio Transforms
Haque, A., Guo, M., & Verma, P. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-38 · Cited by 39
Generative Adversarial Networks in Human Emotion Synthesis: A Review
Hajarolasvadi, N., Ramírez, M. A., Beccaro, W., & Demirel, H. (2020) · IEEE Access · doi:10.1109/access.2020.3042328 · Cited by 42
The Voicemos Challenge 2023: Zero-Shot Subjective Speech Quality Prediction for Multiple Domains
Cooper, E., Huang, W.-C., Tsao, Y., Wang, H., Toda, T., & Yamagishi, J. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389763 · Cited by 72
“The Voice Conversion Challenge (VCC) is a shared task similar to Blizzard but focusing on speech-to-speech conversion to change the speaker identity [11–13].”
BackgroundSelf-citationSpeaker Anonymization for Personal Information Protection Using Voice Conversion Techniques
Yoo, I.-C., Lee, K., Leem, S.-G., Oh, H., Ko, B., & Yook, D. (2020) · IEEE Access · doi:10.1109/access.2020.3035416 · Cited by 30
“We used the voice conversion challenge (VCC) 2016 corpus [23] to evaluate the performance of speaker anonymization techniques in terms of speaker identification and speech recognition accuracies.”
MethodFusion of Self-supervised Learned Models for MOS Prediction
Yang, Z., Zhou, W., Chu, C., Li, S., Dabre, R., Rubino, R., & Zhao, Y. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10262 · Cited by 37
An Adaptive-Learning-Based Generative Adversarial Network for One-to-One Voice Conversion
Dhar, S., Jana, N. D., & Das, S. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3149858 · Cited by 40
“The proposed model is tested on the Voice Conversion Challenge (VCC) 2016 [15], 2018 [16], and 2020 [17] datasets.”
MethodTransformation 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
“We conducted the experiments on the Voice Conversion Challange (VCC) 2016 dataset [35], [36] to assess the performance of the proposed prosody conversion framework for F0, energy contour and duration with parallel training data.”
MethodRefining the evaluation of speech synthesis: A summary of the Blizzard Challenge 2023
Perrotin, O., Stephenson, B., Gerber, S., Bailly, G., & King, S. (2024) · Computer Speech & Language · doi:10.1016/j.csl.2024.101747 · Cited by 45
“It is the mainstay of benchmark competitions – the Blizzard Challenges and various Voice Conversion Challenges (Toda et al., 2016; Lorenzo-Trueba et al., 2018; Yi et al., 2020; Huang et al., 2023) – mainly because it is simple and quick to implement, scales well to a large number of experimental conditions, and the re…”
Voice Conversion for Persons with Amyotrophic Lateral Sclerosis
Zhao, Y., Kuruvilla-Dugdale, M., & Song, M. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2961844 · Cited by 31
“Although different from the problem we address here, for summaries about VC between healthy speakers, please refer to the VC challenges of 2016 and 2018 [6], [7].”
BackgroundOn the use of I-vectors and average voice model for voice conversion without parallel data
Wu, J., Wu, Z., & Xie, L. (2016) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2016.7820901 · Cited by 26
“Voice conversion (VC) is a technique to modify the voice spoken by one speaker (source) so that it sounds like it is spoken by another speaker (target) while retaining its linguistic information [1] [2].”
BackgroundSelf-citationChoi, Y., Jung, Y., & Kim, H. (2021) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt48900.2021.9383533 · Cited by 28
Speechlmscore: Evaluating Speech Generation Using Speech Language Model
Maiti, S., Peng, Y., Saeki, T., & Watanabe, S. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095710 · Cited by 56
“The dataset contains speech from three main sources: i) voice conversion challenges (VCC) from 2016, 2018 and 2020, a total of 79 systems [26–28], ii) more recent text-to-speech models trained with ESPnet [29] on LJspeech [30], 10 systems, and iii) older speech synthesis systems from past Blizzard…”
BackgroundKinnunen, T., Lorenzo-Trueba, J., Yamagishi, J., Toda, T., Saito, D., Villavicencio, F., & Ling, Z.-H. (2018) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2018-27 · Cited by 31
Self-citationTraining 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
“However, the speech parameters generated from these models tend to be over-smoothed, and the quality of their speech is still low compared with that of natural speech [1, 6].”
BackgroundDeep MOS Predictor for Synthetic Speech Using Cluster-Based Modeling
Choi, Y., Jung, Y., & Kim, H. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2111 · Cited by 26
Saito, Y., Takamichi, S., & Saruwatari, H. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461714 · Cited by 24
“However, in training the acoustic models, an over-smoothing effect is often observed in generated vocoder parameters or STFT spectra and significantly degrades synthetic speech quality [9, 14].”
Electrolaryngeal Speech Enhancement with Statistical Voice Conversion based on CLDNN
Kobayashi, K., & Toda, T. (2018) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2018.8553154 · Cited by 25
“Recently, statistical VC techniques have been significantly improved in the area of speaker individuality conversion [10].”
BackgroundSelf-citationApplications of Deep Learning to Audio Generation
Zhao, Y., Xia, X., & Togneri, R. B. (2019) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2019.2945210 · Cited by 23
“Via suitable modification of the speech waveform, voice conversion can convert non-/para-linguistic information as expected [10].”
Oyamada, 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
“The similarity of the converted speech was evaluated according to the evaluation method described in Voice Conversion Challenge 2016 [28].”
MethodOne-Shot Voice Conversion Using Star-Gan
Wang, R., Ding, Y., Li, L., & Fan, C. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053842 · Cited by 31
“VC Challenge (VCC) has been held in the past several years [4, 5] and attracted a lot of attention from academic and industrial participants.”
BackgroundRectified Adam Optimizer-Based CNN Model for Speaker Identification
Mazumder, A., Ghosh, S., Roy, S., Dhar, S., & Jana, N. D. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-0825-5_16 · Cited by 19
On Using Backpropagation for Speech Texture Generation and Voice Conversion
Chorowski, J., Weiss, R. J., Saurous, R. A., & Samy Bengio, A. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461282 · Cited by 19
Voice conversion spoofing detection by exploring artifacts estimates
Hemavathi, R., & Kumaraswamy, R. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10212-0 · Cited by 24
“To evaluate performance of the proposed technique Voice Conversion Challenge 2016 dataset (VCC-2016) [31] and Voice Conversion Challenge 2018 datasets [19] are used.”
MethodLanguage Agnostic Speaker Embedding for Cross-Lingual Personalized Speech Generation
Zhou, Y., Tian, X., & Li, H. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3125142 · Cited by 25
Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
Du, Z., Şişman, B., Zhou, K., & Li, H. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9687906 · Cited by 31
NU Voice Conversion System for the Voice Conversion Challenge 2018
Tobing, P. L., Wu, Y.-C., Hayashi, T., Kobayashi, K., & Toda, T. (2018) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2018-31 · Cited by 19
“The growing interest in VC development motivated many researchers around the world to conceive the 1 Voice Conversion Challenge in 2016 [7].”
BackgroundSelf-citationMulti-Task WaveRNN With an Integrated Architecture for Cross-Lingual Voice Conversion
Zhou, Y., Tian, X., & Li, H. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.3010163 · Cited by 19
“For English, we selected 96 speakers from five database: VCTK [44], CMU ARCTIC [45], VCC2016 [46] and VCC2018 [47].”
MethodKobayashi, K., Toda, T., & Nakamura, S. (2016) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2016.7846338 · Cited by 16
“In the Voice Conversion Challenge 2016 (VCC 2016) [24], only a part of the DIFFSVC framework has been successfully applied to normal VC and our developed VC system still needs to use the vocoding processing for performing the F0 transformation because the direct residual signal modification tends to cause quality degr…”
MethodSelf-citationLombard Speech Synthesis Using Transfer Learning in a Tacotron Text-to-Speech System
Bollepalli, B., Juvela, L., & Alku, P. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1333 · Cited by 25
“We used an evaluation setup similar to [38] for the style similarity test.”
BackgroundMethodIntroduction to Voice Presentation Attack Detection and Recent Advances
Sahidullah, M., Delgado, H., Todisco, M., Nautsch, A., Wang, X., Kinnunen, T., Evans, N., Yamagishi, J., & Lee, K. A. (2023) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-19-5288-3_13 · Cited by 21
Self-citationOkamoto, T., Ohtani, Y., Toda, T., & Kawai, H. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446890 · Cited by 14
“The subjects were then asked to rate the speaker similarity of the two samples on a four-point scale: (4) same speaker, absolutely sure, (3) same speaker, not sure, (2) different speaker, not sure, (1) different speaker, absolutely sure [31].”
BackgroundSelf-citationCycleGAN-VC-GP: Improved CycleGAN-based Non-parallel Voice Conversion
Wang, C., & Yu, Y. (2020) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct50939.2020.9295938 · Cited by 13
“The proposed method is evaluated on the Voice Conversion Challenge 2016 (VCC 2016) dataset [16].”
MethodZero-Shot Voice Conversion with Adjusted Speaker Embeddings and Simple Acoustic Features
Tan, Z., Wei, J., Xu, J., He, Y., & Lu, W. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414975 · Cited by 20
“In recent years, voice conversion challenge (VCC) [6,7] has attracted extensive attention and fully demonstrated the application potential of VC technology.”
BackgroundECAPA-TDNN for Multi-speaker Text-to-speech Synthesis
Xue, J., Deng, Y., Han, Y., Li, Y., Sun, J., & Liang, J. (2022) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.1109/iscslp57327.2022.10037956 · Cited by 23
Bollepalli, B., Juvela, L., Airaksinen, M., Valentini-Botinhao, C., & Alku, P. (2019) · Speech Communication · doi:10.1016/j.specom.2019.04.008 · Cited by 14
“To be used in the evaluation of the Lombard-adapted speech signals of the current study, we modified the setup used in [55] to measure speaker similarity.”
A Compact Framework for Voice Conversion Using Wavenet Conditioned on Phonetic Posteriorgrams
Lu, H., Wu, Z., Li, R., Kang, S., Jia, J., & Meng, H. M. L. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682938 · Cited by 15
“Followed voice conversion challenge 2016 [24], we conducted Mean Opinion Score (MOS) listening test for naturalness and use Same/Different paradigm to measure the speaker similarity.”
MethodSelf-citationTobing, P. L., Wu, Y.-C., & Toda, T. (2020) · doi:10.21437/vcc_bc.2020-23 · Cited by 15
Self-citationGLGAN-VC: A Guided Loss-Based Generative Adversarial Network for Many-to-Many Voice Conversion
Dhar, S., Jana, N. D., & Das, S. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3335119 · Cited by 15
“We tested the proposed model on the VCC 2016 parallel [18] and VCC 2018 nonparallel uni-lingual [16] speech datasets.”
Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speech
Choi, Y., Jung, Y., Suh, Y.-J., & Kim, H. (2022) · IEEE Access · doi:10.1109/access.2022.3175810 · Cited by 20
A Modularized Neural Network with Language-Specific Output Layers for Cross-Lingual Voice Conversion
Zhou, Y., Tian, X., Yılmaz, E., Das, R. K., & Li, H. (2019) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru46091.2019.9003798 · Cited by 11
“10 English speakers (5 female and 5 male) from VCC2016 database [42] and 10 Mandarin speakers (5 female and 5 male) from the Mandarin average model database 1 were chosen for training.”
MethodLuo, Z., Chen, J., Takiguchi, T., & Ariki, Y. (2019) · APSIPA Transactions on Signal and Information Processing · doi:10.1017/atsip.2019.3 · Cited by 11
“So far, spectral mapping mechanisms have achieved tremendous success in VC tasks [1–4], while, how to effectively generate prosody in the target voice remains a challenge.”
BackgroundSaito, Y., Takamichi, S., & Saruwatari, H. (2019) · Computer Speech & Language · doi:10.1016/j.csl.2019.05.008 · Cited by 11
CycleGAN Voice Conversion of Spectral Envelopes using Adversarial Weights
Ferro, R., Obin, N., & Röebel, A. (2020) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco47968.2020.9287643 · Cited by 14
“Over the past few years, VC has largely gained in popularity and in quality [1], [2], in particular with the development of neural voice conversion algorithms [3], [4].”
BackgroundAn Analysis of Performance Evaluation Metrics for Voice Conversion Models
Akhter, M. T., Banerjee, P., Dhar, S., & Jana, N. D. (2022) · IEEE India Conference · doi:10.1109/indicon56171.2022.10040000 · Cited by 10
“6 for the original and the converted speech samples (using CycleGAN-VC [13] for VCC 2016 [32] speech data).”
MethodData augmentation based non-parallel voice conversion with frame-level speaker disentangler
Chen, B., Xu, Z., & Yu, K. (2021) · Speech Communication · doi:10.1016/j.specom.2021.10.001 · Cited by 12
SQAPP: No-Reference Speech Quality Assessment Via Pairwise Preference
Manocha, P., Jin, Z., & Finkelstein, A. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746615 · Cited by 12
“) For models that do not use P ESQ calibration, we observe a significant drop in correlations across datasets including HiFi, VCC16, VCC18 and HiFi2.”
BackgroundInfluentialA novel approach to remove outliers for parallel voice conversion
Shah, N. J., & Patil, H. A. (2019) · Computer Speech & Language · doi:10.1016/j.csl.2019.03.009 · Cited by 10
Kumar, V. D., Swathi, P. G., Jahangir, A., Sah, N. K., & Vinothkumar, V. (2021) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-7998-6870-5.ch025 · Cited by 9
Non-intrusive speech quality assessment: A survey
Shen, K., Yan, D., Hu, J., & Ye, Z. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127471 · Cited by 11
Many-to-many Cross-lingual Voice Conversion with a Jointly Trained Speaker Embedding Network
Zhou, Y., Tian, X., Das, R. K., & Li, H. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023277 · Cited by 11
“Training VCTK [35] English 1,296 utterances 294, 297, 299, 300, 301, 303, 305, 306 8 male, 8 female 302, 311, 315, 316, 334, 345, 360, 363 CMU ARCTIC [36] English 972 utterances slt, clb, lnh 3 male, 3 female bdl, jmk, rms VCC2016 [37] English 810 utterances SF1, SF2, SF3, TF1, TF2 5 male, 5 female SM1, SM2, TM1, TM2,…”
Generation and Detection of Media Clones
Echizen, I., Babaguchi, N., Yamagishi, J., Nitta, N., Nakashima, Y., Nakamura, K., Kono, K., Fang, F., Myojin, S., Kuang, Z., et al. (2020) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2020mui0002 · Cited by 9
“In the 2016 Challenge, a standard VC task using a parallel database was adopted [79].”
MethodSelf-citationAC-VC: Non-Parallel Low Latency Phonetic Posteriorgrams Based Voice Conversion
Ronssin, D., & Cerňak, M. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688277 · Cited by 10
Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations
Benaroya, L., Obin, N., & Röebel, A. (2023) · Entropy · doi:10.3390/e25020375 · Cited by 14
Novel Amplitude Scaling method for bilinear frequency Warping-based Voice Conversion
Shah, N. J., & Patil, H. A. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953212 · Cited by 8
“VC challenge database contains parallel training utterances 5 source and 5 target speakers’ [22].”
BackgroundMethodDetection of Synthetic Speech Based on Spectrum Defects
Deng, J., Mao, T., Yan, D., Dong, L., & Dong, M. (2022) · doi:10.1145/3552466.3556529 · Cited by 9
“Deep learning [2, 5] based on voice conversion (VC) [8, 14] and text-to-speech synthesis (TTS) [9, 16, 17] techniques are used to synthesize speech similar to those of humans to enhance human-computer interaction.”
MethodOn the analysis and evaluation of prosody conversion techniques
Şişman, B., Lee, G., Li, H., & Tan, K. C. (2017) · International Conference on Asian Language Processing · doi:10.1109/ialp.2017.8300542 · Cited by 8
“We conducted the experiments using the Voice Conversion Challenge dataset [28] to assess the performance of the prosody conversion frameworks.”
MethodStructured Sparse Spectral Transforms and Structural Measures for Voice Conversion
Zhao, Y., Kuruvilla-Dugdale, M., & Song, M. (2018) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2018.2860682 · Cited by 8
“Although much progress has been made over the years, the 2016 Voice Conversion Challenge [20], [21] has revealed that the speech quality of converted voices is still below that of natural speech by a large margin, and objective measures that closely correlate with human perception need to be developed to facilitate VC…”
InfluentialVoice conversion with SI-DNN and KL divergence based mapping without parallel training data
Xie, F., Soong, F. K., & Li, H. (2018) · Speech Communication · doi:10.1016/j.specom.2018.11.007 · Cited by 8
Voice Conversion Using Conditional CycleGAN
Yook, D., Yoo, I.-C., & Yoo, S. (2018) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci46756.2018.00290 · Cited by 8
“We used female data (SF1) and male data (TM3) from obtained from an English speech dataset VCC2016 [10] for the preliminary experiments.”
MethodEzzine, K., Martino, J. D., & Frikha, M. (2023) · Applied Sciences · doi:10.3390/app132111988 · Cited by 9
MOS Predictor for Synthetic Speech with I-Vector Inputs
Liu, M., Wang, J., Li, S., Xiang, F., Yao, Y., & Yang, L. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747533 · Cited by 8
Kinnunen, T., Hautamäki, R. G., Vestman, V., & Sahidullah, M. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683811 · Cited by 10
Detection of Replay Attack Based on Normalized Constant Q Cepstral Feature
Ye, Y., Lao, L., Yan, D., & Lin, L. (2019) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda.2019.8725688 · Cited by 7
Generalization of Spectrum Differential based Direct Waveform Modification for Voice Conversion
Huang, W.-C., Wu, Y.-C., Kobayashi, K., Peng, Y., Hwang, H.-T., Tobing, P. L., Tsao, Y., Wang, H., & Toda, T. (2019) · ISCA Speech Synthesis Workshop (SSW) · doi:10.21437/ssw.2019-11 · Cited by 8
“In the Voice Conversion Challenge (VCC) 2016 [26], a predecessor version [25] was evaluated as one of the best systems achieving the best conversion accuracy on speaker identity and high speech quality.”
MethodSelf-citationHernández-Nava, C. A., Rincón-García, E. A., Lara-Velázquez, P., de-los-Cobos-Silva, S. G., Andrade, M. Á. G., & Mora-Gutiérrez, R. A. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1740 · Cited by 6
Generative adversarial networks for whispered to voiced speech conversion: a comparative study
Wagner, D., Baumann, I., & Bocklet, T. (2024) · International Journal of Speech Technology · doi:10.1007/s10772-024-10161-1 · Cited by 8
“We employed a model pre-trained on Voice Conversion Challenge 2018 (VCC 2018) (Lorenzo-Trueba et al., 2018) and Voice Conversion Challenge 2016 (VCC 2016) (Toda et al., 2016) data.”
Multidimensional scaling of systems in the Voice Conversion Challenge 2016
Wester, M., Wu, Z., & Yamagishi, J. (2016) · ISCA Speech Synthesis Workshop (SSW) · doi:10.21437/ssw.2016-7 · Cited by 6
“Introduction The Voice Conversion Challenge (VCC) 2016 [1], one of the special sessions at Interspeech 2016, was devised to better understand different voice conversion techniques.”
BackgroundMethodSelf-citationNovel Inter Mixture Weighted GMM Posteriorgram for DNN and GAN-based Voice Conversion
Shah, N. J., Sreeraj, R., Shah, N., & Patil, H. A. (2018) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipa.2018.8659638 · Cited by 6
“The VCC 2016 database consists of training utterances from 5 source and 5 target speakers [40].”
Background
Metadata
- Authors
- Toda, T., Chen, L.-H., Saito, D., Villavicencio, F., Wester, M., Wu, Z., & Yamagishi, J.
- Affiliations
- Nagoya University (JP)
- University of Science and Technology of China (CN)
- The University of Tokyo (JP)
- National Institute of Informatics (JP)
- University of Edinburgh (GB)
- Venue
- Interspeech 2016
- Publisher
- ISCA
- Published
- 2016-09-08
- Pages
- 1632-1636
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2473388484
- Cited by
- 156
- References
- 40
- Citations by year
- 2026: 5 · 2025: 6 · 2024: 12 · 2023: 16 · 2022: 18 · 2021: 20 · 2020: 21 · 2019: 25 · 2018: 14 · 2017: 11 · 2016: 8
- FWCI
- 10.42
- Type
- conference paper
- Language
- en
- Open access
- Licence
- other-oa
- Locations
- Interspeech (USB) (publishedVersion)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, other-oa)
- Funders
- Engineering and Physical Sciences Research Council (EP/J002526/1, EP/I031022/1)
- Japan Society for the Promotion of Science (26280060)
- 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, naturalness evaluation, listener evaluation, speech synthesis
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.