Related papers: Self-imitating Feedback Generation Using GAN for C…

While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce \textbf{G}enerative…

Singing voice conversion aims to convert singer's voice from source to target without changing singing content. Parallel training data is typically required for the training of singing voice conversion system, that is however not practical…

I-vector based text-independent speaker verification (SV) systems often have poor performance with short utterances, as the biased phonetic distribution in a short utterance makes the extracted i-vector unreliable. This paper proposes an…

Generative models have gained more and more attention in recent years for their remarkable success in tasks that required estimating and sampling data distribution to generate high-fidelity synthetic data. In speech, text-to-speech…

We investigated an enhancement and a domain adaptation approach to make speaker verification systems robust to perturbations of far-field speech. In the enhancement approach, using paired (parallel) reverberant-clean speech, we trained a…

Nowadays, recognition-synthesis-based methods have been quite popular with voice conversion (VC). By introducing linguistics features with good disentangling characters extracted from an automatic speech recognition (ASR) model, the VC…

This paper presents a novel approach for the automatic generation of Cued Speech (ACSG), a visual communication system used by people with hearing impairment to better elicit the spoken language. We explore transfer learning strategies by…

This paper proposes Transducers with Pronunciation-aware Embeddings (PET). Unlike conventional Transducers where the decoder embeddings for different tokens are trained independently, the PET model's decoder embedding incorporates shared…

Advances in neural speech synthesis have brought us technology that is not only close to human naturalness, but is also capable of instant voice cloning with little data, and is highly accessible with pre-trained models available.…

Speech synthesis is an important practical generative modeling problem that has seen great progress over the last few years, with likelihood-based autoregressive neural models now outperforming traditional concatenative systems. A downside…

Generative Adversarial Networks (GAN) is a model for data synthesis, which creates plausible data through the competition of generator and discriminator. Although GAN application to image synthesis is extensively studied, it has inherent…

Speech enhancement deep learning systems usually require large amounts of training data to operate in broad conditions or real applications. This makes the adaptability of those systems into new, low resource environments an important…

Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate high quality…

Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectrum while the vocoder generates waveform from the…

We present an unsupervised non-parallel many-to-many voice conversion (VC) method using a generative adversarial network (GAN) called StarGAN v2. Using a combination of adversarial source classifier loss and perceptual loss, our model…

In this work, we propose a method for training distributed GAN with sequential temporary discriminators. Our proposed method tackles the challenge of training GAN in the federated learning manner: How to update the generator with a flow of…

It is still a challenging task to learn a neural text generation model under the framework of generative adversarial networks (GANs) since the entire training process is not differentiable. The existing training strategies either suffer…

We propose a computational model of speech production combining a pre-trained neural articulatory synthesizer able to reproduce complex speech stimuli from a limited set of interpretable articulatory parameters, a DNN-based internal forward…

This work provides a solution to the challenge of small amounts of training data in Non-Destructive Ultrasonic Testing for composite components. It was demonstrated that direct simulation alone is ineffective at producing training data that…

Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech…