An overview of voice conversion systems

By Seyed Hamidreza Mohammadi, A. Kain. Speech Communication, 2017

298 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/f7fb20555f27ee2098bbb89bf3617ef278d0b659

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

An Investigation of Subband Wavenet Vocoder Covering Entire Audible Frequency Range with Limited Acoustic Features (2018, background): “In conventional statistical parametric speech synthesis (SPSS) [1] and voice conversion (VC) [2], source-ﬁlter model-based vocoders are typically introduced to synthesize speech waveforms from estimated and converted acoustic features that are mainly constructed from the fundamental frequency and…”
Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion (2022, background): “Voice conversion (VC) is a speech task that studies how to convert one’s voice to sound like that of another while preserving the linguistic content of the source speaker [1, 2].”
AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models (2023, unknown): “Speech voice conversion [2, 35, 44, 43] and singing voice conversion [7, 28] aim to modify the timbre without changing the speech or singing content.”
An Overview of Voice Conversion and Its Challenges: From Statistical Modeling to Deep Learning (2020, background): “Wu and Li [6], and Mohammadi and Kain [35] provided an overview of voice conversion systems from the perspective of time alignment of speech features followed by feature mapping, that represents the statistical modeling school of thought.”
Axial Residual Networks for CycleGAN-based Voice Conversion (2021, background): “Even fairly recent VC models often necessitate a parallel dataset, a set of texts spoken twice, respectively by the source speaker and the target speaker [1].”
Low-Resource Expressive Text-To-Speech Using Data Augmentation (2020, methodology): “Much research has already been conducted on VC [21–24].”
Emotional Voice Conversion: Theory, Databases and ESD (2021, methodology): “Typically voice conversion is used to describe speaker voice conversion, which seeks to convert speaker identity from one to another without changing the linguistic content (Mohammadi and Kain, 2017; Sisman et al., 2020), as shown in Fig.”
Improving FFTNet Vocoder with Noise Shaping and Subband Approaches (2018, methodology): “In conventional statistical parametric speech synthesis (SPSS) [1] and voice conversion (VC) [2], source-ﬁlter vocoders are typically employed to synthesize speech waveforms from estimated and converted acoustic features.”
An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era (2022, background): “Two recent comprehensive reviews of VC can be found in [85] and [86].”