Spectral Mapping Using Artificial Neural Networks for Voice Conversion

By Srinivas Desai, Alan W. Black, Bayya Yegnanarayana, Kishore Prahallad. 2010

263 citations recorded by the source corpus.

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

Neural Voice Cloning with a Few Samples (2018, methodology): “There are also approaches to model spectral conversion using neural networks such as (Desai et al., 2010), (Chen et al.”
A Deep Generative Architecture for Postfiltering in Statistical Parametric Speech Synthesis (2015, methodology): “However, the conventional approaches for VC, such as the ones based on GMMs and conventional neural networks (NN) [23], still suffer from the over-smoothing problem caused by the statistical averaging of the underlying model.”
Automatic Building of Synthetic Voices from Audio Books (2010, methodology): “Hence, nonlinear models such as artificial neural networks are explored to approximate the mapping function [Srinivas et al., 2010].”
Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations (2018, background): “In general, among the difﬁcult problems for VC approaches, the need of aligned data [11, 12, 13, 14, 15, 16, 17], and over-smoothing of signals [1, 18, 19] are two examples carefully studied.”
Emotional Voice Conversion: Theory, Databases and ESD (2021, background): “Thus, spectrum conversion has been the focus [27, 28, 29].”
CycleGAN-VC: Non-parallel Voice Conversion Using Cycle-Consistent Adversarial Networks (2018, methodology): “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) ”
A probabilistic interpretation for artificial neural network-based voice conversion (2015, methodology): “ANN (baseline): Conventional ANN-based VC [6].”
Voice Conversion Using Deep Neural Networks With Layer-Wise Generative Training (2014, methodology): “Previously, voice conversion using neural networks has been studied in [17], [18], where the neural networks were trained using the back propagation (BP) algorithm with the minimum mean square error (MMSE) criterion.”
Conditional restricted Boltzmann machine for voice conversion (2013, methodology): “In addition, methods, such as neural network [5, 6] and dynamic kernel partial least squares regression [7] have also been proposed to learn the non-linear relationship between source and target speech.”
Voice conversion from non-parallel corpora using variational auto-encoder (2016, methodology): “A wide variety of techniques have been applied to spectral conversion, including Gaussian mixture models (GMM) [1]– [3], frequency warping [4], [5], deep neural networks (DNN) [6]–[8], and exemplar-based approaches [9], [10].”
Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling (2020, methodology): “target acoustic features, which can be Gaussian mixture models (GMMs) [2], [3], artificial neural networks (ANNs) [4]–[7], etc.”
An Overview of Voice Conversion and Its Challenges: From Statistical Modeling to Deep Learning (2020, unknown): “tests [13], [40], [61], [62], [264]–[268].”
WaveNet Vocoder with Limited Training Data for Voice Conversion (2018, methodology): “In this approach, the acoustic features extracted from the source speech are first mapped toward the target speaker using a conversion model, which could be a Gaussian mixture model (GMM) [1, 2, 3], an artificial neural network (ANN) [4, 5] and so on.”
High-Quality Nonparallel Voice Conversion Based on Cycle-Consistent Adversarial Network (2018, methodology): “[14] used a feed forward neural network (NN) as the mapping model, in which the features that are similar are paired and serve as input and supervisor signals for parameter training.”
StarGAN-VC: non-parallel many-to-many Voice Conversion Using Star Generative Adversarial Networks (2018, background): “Recently, a neural network (NN)-based framework based on feed-forward deep NNs [11–13], recurrent NNs [14], and generative adversarial nets (GANs) [7], and an exemplarbased framework based on non-negative matrix factorization (NMF) [15, 16] have also proved successful.”
Spoofing and countermeasures for speaker verification: A survey (2015, background): “Alternative, nonlinear approaches include those based on neural networks (Desai et al., 2010), dynamic kernel partial least squares (Helander et al., 2012), restricted Boltzmann machines (Chen et al., 2013) and deep belief networks (Nakashika et al., 2013).”
Many-to-Many Voice Transformer Network (2020, background): “square regression [11], frequency warping [12], non-negative matrix factorization [13], group sparse representation [14], fully connected deep neural networks (DNNs) [15], [16], and long-”