The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods

By Jaime Lorenzo-Trueba, Junichi Yamagishi, Tomoki Toda, Daisuke Saito, Fernando Villavicencio, Tomi H. Kinnunen, Zhenhua Ling. 2018

351 citations recorded by the source corpus.

We present the Voice Conversion Challenge 2018, designed as a follow up to the 2016 edition with the aim of providing a common framework for evaluating and comparing different state-of-the-art voice conversion (VC) systems. The objective of the challenge was to perform speaker conversion (i.e. transform the vocal identity) of a source speaker to a target speaker while maintaining linguistic information. As an update to the previous challenge, we considered both parallel and non-parallel data to form the Hub and Spoke tasks, respectively. A total of 23 teams from around the world submitted their systems, 11 of them additionally participated in the optional Spoke task. A large-scale crowdsourced perceptual evaluation was then carried out to rate the submitted converted speech in terms of naturalness and similarity to the target speaker identity. In this paper, we present a brief summary of the state-of-the-art techniques for VC, followed by a detailed explanation of the challenge tasks and the results that were obtained.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale (2023, background): “Voice conversion [27, 39], emotion conversion [53, 34], speech enhancement [63, 11, 55] belong to this category.”
A Survey on Neural Speech Synthesis (2021, neutral): “05 English LibriSpeech [253] 982 2484 16 English LibriTTS [421] 586 2456 24 English VCC 2018 [208] 1 12 22.”
Zero-Shot Multi-Speaker Text-To-Speech with State-Of-The-Art Neural Speaker Embeddings (2019, methodology): “…test utterance at a time and ﬁrst rated it on a Likert scale from 1-5 for Mean Opinion Score (MOS) for naturalness, then rated for speaker similarity compared to a reference utter-ance on a Differential MOS (DMOS) scale [41] from 1 (deﬁnitely a different speaker) to 4 (deﬁnitely the same speaker).”
ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild (2022, background): “They are the 2018 [31] and 2020 [32] voice conversion challenge (VCC) databases.”
Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos (2019, background): “Moreover, thanks to advances in speech synthesis and voice conversion [19], an attacker can also clone a person’s voice (only a few minutes of speech are needed) and synchronize it with the visual component to create an audiovisual spoof [29, 9].”
Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling (2020, result): “PPG-VC: This baseline approach has a network architecture similar to the N10 system [46] in VCC2018 [47].”
SpeechNet: A Universal Modularized Model for Speech Processing Tasks (2021, methodology): “Here we perform parallel VC (Desai et al., 2009; Lorenzo-Trueba et al., 2018), where we have the target converted speech as groundtruth for each source speech during training.”
Didispeech: A Large Scale Mandarin Speech Corpus (2020, methodology): “For English speech synthesis, VCTK [16] and VCC 2018 [17] have been widely used in the research of multi-speaker TTS and VC respectively.”
TTS Skins: Speaker Conversion via ASR (2019, methodology): “The 2018 voice conversion challenge (VCC2018) [7] evaluated 23 voice conversion systems on two tasks.”
ASVspoof 2019: Automatic Speaker Veriﬁcation Spooﬁng and Countermeasures Challenge Evaluation Plan ∗ (2021, background): “The best performing system in the Voice Conversion Challenge 2018 [6] also produces converted voice signals with greatly improved naturalness and speaker similarity than the best performing systems in 2015.”
WaveNet Vocoder with Limited Training Data for Voice Conversion (2018, methodology): “We evaluated the proposed method on the VCC 2018 HUB task [27], which was a parallel training task.”
Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, methodology): “Multiple Voice Conversion Challenges (VCC) have been held to encourage the development of VC generation techniques and improve the quality of converted speech [137, 241, 242].”
Many-to-Many Voice Transformer Network (2020, methodology): “2 Note that this method was used as a baseline in the Voice Conversion Challenge (VCC) 2018 [75].”
NAUTILUS: A Versatile Voice Cloning System (2020, methodology): “4) Scenario conclusion: Even though the naturalness of our voice cloning system was slightly worse than N10 (again the best system at VCC2018), generally speaking it has achieved performance that is comparable to SOTA systems considering the difference in experimental conditions (e.g., the amount of”
MBNET: MOS Prediction for Synthesized Speech with Mean-Bias Network (2021, methodology): “We use the MOS dataset from Voice Conversion Challenge 2018 (VCC 2018) [19] to train MBNet.”