Related papers: Hierarchical Generative Modeling for Controllable …
Despite rapid advances in the field of emotional text-to-speech (TTS), recent studies primarily focus on mimicking the average style of a particular emotion. As a result, the ability to manipulate speech emotion remains constrained to…
Neural text-to-speech synthesis (NTTS) models have shown significant progress in generating high-quality speech, however they require a large quantity of training data. This makes creating models for multiple styles expensive and…
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…
This paper proposes a zero-shot text-to-speech (TTS) conditioned by a self-supervised speech-representation model acquired through self-supervised learning (SSL). Conventional methods with embedding vectors from x-vector or global style…
Using a text description as prompt to guide the generation of text or images (e.g., GPT-3 or DALLE-2) has drawn wide attention recently. Beyond text and image generation, in this work, we explore the possibility of utilizing text…
Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech…
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…
Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterances in a dialogue. In an effort to model this kind of generative process, we propose a neural…
Flow-based generative models are widely used in text-to-speech (TTS) systems to learn the distribution of audio features (e.g., Mel-spectrograms) given the input tokens and to sample from this distribution to generate diverse utterances.…
Speaker-adaptive Text-to-Speech (TTS) synthesis has attracted considerable attention due to its broad range of applications, such as personalized voice assistant services. While several approaches have been proposed, they often exhibit high…
There has been a significant progress in Text-To-Speech (TTS) synthesis technology in recent years, thanks to the advancement in neural generative modeling. However, existing methods on any-speaker adaptive TTS have achieved unsatisfactory…
Recently, synthesizing personalized speech by text-to-speech (TTS) application is highly demanded. But the previous TTS models require a mass of target speaker speeches for training. It is a high-cost task, and hard to record lots of…
Many factors influence speech yielding different renditions of a given sentence. Generative models, such as variational autoencoders (VAEs), capture this variability and allow multiple renditions of the same sentence via sampling. The…
Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and…
Some recent studies have demonstrated the feasibility of single-stage neural text-to-speech, which does not need to generate mel-spectrograms but generates the raw waveforms directly from the text. Single-stage text-to-speech often faces…
In this paper, we present a Diffusion GAN based approach (Prosodic Diff-TTS) to generate the corresponding high-fidelity speech based on the style description and content text as an input to generate speech samples within only 4 denoising…
Recently, deep learning-based Text-to-Speech (TTS) systems have achieved high-quality speech synthesis results. Recurrent neural networks have become a standard modeling technique for sequential data in TTS systems and are widely used.…
Text-to-speech models trained on large-scale datasets have demonstrated impressive in-context learning capabilities and naturalness. However, control of speaker identity and style in these models typically requires conditioning on reference…
Recent advances in neural multi-speaker text-to-speech (TTS) models have enabled the generation of reasonably good speech quality with a single model and made it possible to synthesize the speech of a speaker with limited training data.…
This paper proposes an Expressive Speech Synthesis model that utilizes token-level latent prosodic variables in order to capture and control utterance-level attributes, such as character acting voice and speaking style. Current works aim to…