ArticleAdvances in neural information processing systems2023
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models.
Article in Advances in neural information processing systems, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 8 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
8 citing papers in PubMed.
- Decoding intended speech with an intracortical brain-computer interface in a person with long-standing anarthria and locked-in syndrome.Cell reports · 2026Article
- Zero-shot emotional speech synthesis based on feature decoupling and adaptive loss-threshold reweighting.PloS one · 2026Article
- Speech-based early depressive symptom screening using MAX-Net: a multi-scale autoencoder-augmented xLSTM framework.Frontiers in psychiatry · 2026Article
- Article
- Speaker Identity is Robustly Encoded in Spatial Patterns of Intracranial EEG for Attention Decoding.bioRxiv : the preprint server for biology · 2025Article
- An instantaneous voice-synthesis neuroprosthesis.Nature · 2025Article
- Automatic Detection of Articulatory-Based Disfluencies in Primary Progressive Aphasia.IEEE journal of selected topics in signal processing · 2025Article
- An instantaneous voice synthesis neuroprosthesis.bioRxiv : the preprint server for biology · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
Abstract
In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its predecessor by modeling styles as a latent random variable through diffusion models to generate the most suitable style for the text without requiring reference speech, achieving efficient latent diffusion while benefiting from the diverse speech synthesis offered by diffusion models. Furthermore, we employ large pre-trained SLMs, such as WavLM, as discriminators with our novel differentiable duration modeling for end-to-end training, resulting in improved speech naturalness. StyleTTS 2 surpasses human recordings on the single-speaker LJSpeech dataset and matches it on the multispeaker VCTK dataset as judged by native English speakers. Moreover, when trained on the LibriTTS dataset, our model outperforms previous publicly available models for zero-shot speaker adaptation. This work achieves the first human-level TTS on both single and multispeaker datasets, showcasing the potential of style diffusion and adversarial training with large SLMs. The audio demos and source code are available at https://styletts2.github.io/.
Identifiers
39866554PMC11759097What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.