Related papers: Self-imitating Feedback Generation Using GAN for C…
Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep…
We propose a learning-based filter that allows us to directly modify a synthetic speech waveform into a natural speech waveform. Speech-processing systems using a vocoder framework such as statistical parametric speech synthesis and voice…
Learning a new language involves constantly comparing speech productions with reference productions from the environment. Early in speech acquisition, children make articulatory adjustments to match their caregivers' speech. Grownup…
Speech synthesis is used in a wide variety of industries. Nonetheless, it always sounds flat or robotic. The state of the art methods that allow for prosody control are very cumbersome to use and do not allow easy tuning. To tackle some of…
In recent years, Generative Adversarial Networks (GANs) have produced significantly improved results in speech enhancement (SE) tasks. They are difficult to train, however. In this work, we introduce several improvements to the GAN training…
Naturally introduced perturbations in audio signal, caused by emotional and physical states of the speaker, can significantly degrade the performance of Automatic Speech Recognition (ASR) systems. In this paper, we propose a front-end based…
Dysarthria is a motor speech impairment affecting millions of people. Dysarthric speech can be far less intelligible than those of non-dysarthric speakers, causing significant communication difficulties. The goal of our work is to develop a…
Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources. We propose a novel generative model based on cyclic-consistent generative adversarial network (CycleGAN) for…
This paper proposes a source-filter-based generative adversarial neural vocoder named SF-GAN, which achieves high-fidelity waveform generation from input acoustic features by introducing F0-based source excitation signals to a neural filter…
Thanks to their remarkable generative capabilities, GANs have gained great popularity, and are used abundantly in state-of-the-art methods and applications. In a GAN based model, a discriminator is trained to learn the real data…
A method for statistical parametric speech synthesis incorporating generative adversarial networks (GANs) is proposed. Although powerful deep neural networks (DNNs) techniques can be applied to artificially synthesize speech waveform, the…
While generative adversarial networks (GANs) based neural text-to-speech (TTS) systems have shown significant improvement in neural speech synthesis, there is no TTS system to learn to synthesize speech from text sequences with only…
Voice impersonation is not the same as voice transformation, although the latter is an essential element of it. In voice impersonation, the resultant voice must convincingly convey the impression of having been naturally produced by the…
Cycle-consistent generative adversarial networks have been widely used in non-parallel voice conversion (VC). Their ability to learn mappings between source and target features without relying on parallel training data eliminates the need…
This paper presents an adversarial learning method for recognition-synthesis based non-parallel voice conversion. A recognizer is used to transform acoustic features into linguistic representations while a synthesizer recovers output…
Recently, cycle-consistent adversarial network (Cycle-GAN) has been successfully applied to voice conversion to a different speaker without parallel data, although in those approaches an individual model is needed for each target speaker.…
We propose a new framework to improve automatic speech recognition (ASR) systems in resource-scarce environments using a generative adversarial network (GAN) operating on acoustic input features. The GAN is used to enhance the features of…
Speaking rate refers to the average number of phonemes within some unit time, while the rhythmic patterns refer to duration distributions for realizations of different phonemes within different phonetic structures. Both are key components…
Besides the well-known classification task, these days neural networks are frequently being applied to generate or transform data, such as images and audio signals. In such tasks, the conventional loss functions like the mean squared error…
Voice conversion is to generate a new speech with the source content and a target voice style. In this paper, we focus on one general setting, i.e., non-parallel many-to-many voice conversion, which is close to the real-world scenario. As…