Related papers: Varianceflow: High-Quality and Controllable Text-t…

Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we…

We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…

Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contains noise and generally needs to be…

Recently, the application of diffusion models has facilitated the significant development of speech and audio generation. Nevertheless, the quality of samples generated by diffusion models still needs improvement. And the effectiveness of…

Recently, text-to-speech (TTS) models such as FastSpeech and ParaNet have been proposed to generate mel-spectrograms from text in parallel. Despite the advantage, the parallel TTS models cannot be trained without guidance from…

We propose Guided-TTS, a high-quality text-to-speech (TTS) model that does not require any transcript of target speaker using classifier guidance. Guided-TTS combines an unconditional diffusion probabilistic model with a separately trained…

Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function…

For spoken dialog systems to conduct fluid conversational interactions with users, the systems must be sensitive to turn-taking cues produced by a user. Models should be designed so that effective decisions can be made as to when it is…

Diffusion models, and their generalization, flow matching, have had a remarkable impact on the field of media generation. Here, the conventional approach is to learn the complex mapping from a simple source distribution of Gaussian noise to…

Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized…

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…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using…

In this paper we address the problem of enhancing speech signals in noisy mixtures using a source separation approach. We explore the use of neural networks as an alternative to a popular speech variance model based on supervised…

This paper introduces F5-TTS, a fully non-autoregressive text-to-speech system based on flow matching with Diffusion Transformer (DiT). Without requiring complex designs such as duration model, text encoder, and phoneme alignment, the text…

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is important to capture the diversity in human speech such as speaker identities, prosodies, and styles (e.g., singing). Current large TTS systems usually…

Style transfer TTS has shown impressive performance in recent years. However, style control is often restricted to systems built on expressive speech recordings with discrete style categories. In practical situations, users may be…

Flow-based generative models have greatly improved text-to-speech (TTS) synthesis quality, but inference speed remains limited by the iterative sampling process and multiple function evaluations (NFE). The recent MeanFlow model accelerates…

Flow-based text-to-image models follow deterministic trajectories, making it costly to explore diverse modes under limited sampling budgets. Existing approaches to improving diversity often rely on retraining or degrade image fidelity. To…

Language diffusion models aim to improve sampling speed and coherence over autoregressive LLMs. We introduce Neural Flow Diffusion Models for language generation, an extension of NFDM that enables the straightforward application of…