In this paper, we propose SHIFT15M, a dataset that can be used to properly evaluate models in situations where the distribution of data changes between training and testing.
A DNN-based generator is trained using a human-based discriminator, i. e., humans' perceptual evaluations, instead of the GAN's DNN-based discriminator.
In this paper, we investigate the effectiveness of using rich annotations in deep neural network (DNN)-based statistical speech synthesis.
Developing a spontaneous speech corpus would be beneficial for spoken language processing and understanding.
Matching two different sets of items, called heterogeneous set-to-set matching problem, has recently received attention as a promising problem.
To model the human-acceptable distribution, we formulate a backpropagation-based generator training algorithm by regarding human perception as a black-boxed discriminator.
The experimental evaluation compares converted voices between the proposed method that does not use the targeted speaker's voice data and the standard VC that uses the data.
Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to multi-speaker modeling in speech synthesis, it does not correlate with the subjective inter-speaker similarity and is not necessarily appropriate speaker representation for open speakers whose speech utterances are not included in the training data.
To address this problem, we use a GMMN to model the variation of the modulation spectrum of the pitch contour of natural singing voices and add a randomized inter-utterance variation to the pitch contour generated by conventional DNN-based singing voice synthesis.
This paper presents a deep neural network (DNN)-based phase reconstruction from amplitude spectrograms.
Sound Audio and Speech Processing
In the proposed framework incorporating the GANs, the discriminator is trained to distinguish natural and generated speech parameters, while the acoustic models are trained to minimize the weighted sum of the conventional minimum generation loss and an adversarial loss for deceiving the discriminator.
Conventional VC using shared context posterior probabilities predicts target speech parameters from the context posterior probabilities estimated from the source speech parameters.