Analysis of the Voice Conversion Challenge 2016 Evaluation Results

By Mirjam Wester, Zhizheng Wu, Junichi Yamagishi. 2016

77 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, 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 Experimental and Cognitive Psychology

In Signal Processing

Citations in the corpus

Neural Voice Cloning with a Few Samples (2018, methodology): “14 shows the distribution of the scores given by MTurk users as in [Wester et al., 2016].”
Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations (2021, methodology): “Speaker similarity (SSIM (%)) were measured with a binary decision and uncertainty options, following [50].”
High quality, lightweight and adaptable TTS using LPCNet (2019, methodology): “The subject is asked to rate their voice similarity, using a 4-point scale adopted from the Voice Conversion Challenge (VCC) [15] [16], and utilized in our previous experiments [6].”
Locally Linear Embedding for Exemplar-Based Spectral Conversion (2016, methodology): “The external evaluation was conducted by the vcc2016 organizer in terms of naturalness and similarity of the converted speech [26, 27].”
CycleGAN-VC: Non-parallel Voice Conversion Using Cycle-Consistent Adversarial Networks (2018, methodology): “By referring to the VCC 2016 [57], we evaluated the naturalness and speaker similarity of the converted samples.”
Voice Conversion from Unaligned Corpora Using Variational Autoencoding Wasserstein Generative Adversarial Networks (2017, result): “unreported because we found that it remained about the same as that of [13] (System B in [14]).”
Zero-Shot Voice Style Transfer with Only Autoencoder Loss (2019, background): “We follow the design in Wester et al. (2016) to cue the subjects to judge if the speakers are the same, and how conﬁdent they are with their judgment.”
Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation (2020, methodology): “To measure the speaker similarity, the speaker similarity test [30] is conducted.”
NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis (2022, methodology): “We tested the naturalness (MOS) and speaker similarity (SSIM) following Wester et al. (2016).”
An overview of voice conversion systems (2017, methodology): “An extensive subjective evaluation was performed during the 016 VCC, with multiple submitted systems ( Wester et al., 2016a ). t was concluded that “there is still a lot of work to be done n voice conversion, it is not a solved problem.”
Deep Learning Based Assessment of Synthetic Speech Naturalness (2020, background): “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.”
The Voice Conversion Challenge 2016 (2016, background): “A general description of the test is given below, a more detailed description of the listening test design is given in [39].”