Related papers: Style Description based Text-to-Speech with Condit…

Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models. However, the…

Most existing text-to-speech (TTS) systems either synthesize speech sentence by sentence and stitch the results together, or drive synthesis from plain-text dialogues alone. Both approaches leave models with little understanding of global…

Adaptive text to speech (TTS) can synthesize new voices in zero-shot scenarios efficiently, by using a well-trained source TTS model without adapting it on the speech data of new speakers. Considering seen and unseen speakers have diverse…

Unlike human speakers, typical text-to-speech (TTS) systems are unable to produce multiple distinct renditions of a given sentence. This has previously been addressed by adding explicit external control. In contrast, generative models are…

While diffusion models have significantly advanced the quality of image generation their capability to accurately and coherently render text within these images remains a substantial challenge. Conventional diffusion-based methods for scene…

Recent development of neural vocoders based on the generative adversarial neural network (GAN) has shown obvious advantages of generating raw waveform conditioned on mel-spectrogram with fast inference speed and lightweight networks.…

This paper is about developing personalized speech synthesis systems with recordings of mildly impaired speech. In particular, we consider consonant and vowel alterations resulted from partial glossectomy, the surgical removal of part of…

Diffusion models are the mainstream approach for time series generation tasks. However, existing diffusion models for time series generation require retraining the entire framework to introduce specific conditional guidance. There also…

While modern TTS technologies have made significant advancements in audio quality, there is still a lack of behavior naturalness compared to conversing with people. We propose a style-embedded TTS system that generates styled responses…

Current emotional Text-To-Speech (TTS) and style transfer methods rely on reference encoders to control global style or emotion vectors, but do not capture nuanced acoustic details of the reference speech. To this end, we propose a novel…

We enhance the vanilla adversarial training method for unsupervised Automatic Speech Recognition (ASR) by a diffusion-GAN. Our model (1) injects instance noises of various intensities to the generator's output and unlabeled reference text…

In this paper, we present a novel architecture to realize fine-grained style control on the transformer-based text-to-speech synthesis (TransformerTTS). Specifically, we model the speaking style by extracting a time sequence of local style…

Text-to-speech (TTS) synthesis has seen renewed progress under the discrete modeling paradigm. Existing autoregressive approaches often rely on single-codebook representations, which suffer from significant information loss. Even with…

We propose a novel method for generating high-resolution videos of talking-heads from speech audio and a single 'identity' image. Our method is based on a convolutional neural network model that incorporates a pre-trained StyleGAN…

Existing generative models for unsupervised anomalous sound detection are limited by their inability to fully capture the complex feature distribution of normal sounds, while the potential of powerful diffusion models in this domain remains…

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…

Since the introduction of Generative Adversarial Networks (GANs) in speech synthesis, remarkable achievements have been attained. In a thorough exploration of vocoders, it has been discovered that audio waveforms can be generated at speeds…

Machine-generated speech is characterized by its limited or unnatural emotional variation. Current text to speech systems generates speech with either a flat emotion, emotion selected from a predefined set, average variation learned from…

Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform…

Deep learning has led to considerable advances in text-to-speech synthesis. Most recently, the adoption of Score-based Generative Models (SGMs), also known as Diffusion Probabilistic Models (DPMs), has gained traction due to their ability…