English
Related papers

Related papers: Towards Flow-Matching-based TTS without Classifier…

200 papers

Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-09 Yi Ren , Chenxu Hu , Xu Tan , Tao Qin , Sheng Zhao , Zhou Zhao , Tie-Yan Liu

Classifier-free guidance (CFG) is a cornerstone of text-to-image diffusion models, yet its effectiveness is limited by the use of static guidance scales. This "one-size-fits-all" approach fails to adapt to the diverse requirements of…

Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despite these advancements, achieving an optimal balance between…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-28 Jinhyeok Yang , Junhyeok Lee , Hyeong-Seok Choi , Seunghun Ji , Hyeongju Kim , Juheon Lee

Recent advancements in generative modeling, particularly diffusion models, have opened new directions for time series modeling, achieving state-of-the-art performance in forecasting and synthesis. However, the reliance of diffusion-based…

Machine Learning · Computer Science 2025-05-13 Marcel Kollovieh , Marten Lienen , David Lüdke , Leo Schwinn , Stephan Günnemann

Recent advancements in text-to-speech (TTS) have shown that language model (LM) based systems offer competitive performance compared to traditional approaches. However, in training, TTS models use ground-truth (GT) tokens as prefixes to…

Sound · Computer Science 2025-09-23 Ruonan Zhang , Lingzhou Mu , Xixin Wu , Kai Zhang

Flow models have rapidly become the go-to method for training and deploying large-scale generators, owing their success to inference-time flexibility via adjustable integration steps. A crucial ingredient in flow training is the choice of…

Planning is a critical component of end-to-end autonomous driving. However, prevailing imitation learning methods often suffer from mode collapse, failing to produce diverse trajectory hypotheses. Meanwhile, existing generative approaches…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Lin Liu , Guanyi Yu , Ziying Song , Junqiao Li , Caiyan Jia , Feiyang Jia , Peiliang Wu , Yandan Luo

In this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which are trained with the need of external aligners, EfficientTTS…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-08 Chenfeng Miao , Shuang Liang , Zhencheng Liu , Minchuan Chen , Jun Ma , Shaojun Wang , Jing Xiao

Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-28 Ziqian Wang , Zikai Liu , Xinfa Zhu , Yike Zhu , Mingshuai Liu , Jun Chen , Longshuai Xiao , Chao Weng , Lei Xie

Flow matching models have shown great potential in image generation tasks among probabilistic generative models. However, most flow matching models in the literature do not explicitly utilize the underlying clustering structure in the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Anirban Samaddar , Yixuan Sun , Viktor Nilsson , Sandeep Madireddy

Existing large-scale zero-shot text-to-speech (TTS) models deliver high speech quality but suffer from slow inference speeds due to massive parameters. To address this issue, this paper introduces ZipVoice, a high-quality…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-08 Han Zhu , Wei Kang , Zengwei Yao , Liyong Guo , Fangjun Kuang , Zhaoqing Li , Weiji Zhuang , Long Lin , Daniel Povey

Classifier-free guidance (CFG) is a widely used technique for improving the perceptual quality of samples from conditional diffusion models. It operates by linearly combining conditional and unconditional score estimates using a guidance…

Machine Learning · Computer Science 2025-10-02 Alexandre Galashov , Ashwini Pokle , Arnaud Doucet , Arthur Gretton , Mauricio Delbracio , Valentin De Bortoli

Recently, zero-shot text-to-speech (TTS) systems, capable of synthesizing any speaker's voice from a short audio prompt, have made rapid advancements. However, the quality of the generated speech significantly deteriorates when the audio…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-11 Xiaofei Wang , Sefik Emre Eskimez , Manthan Thakker , Hemin Yang , Zirun Zhu , Min Tang , Yufei Xia , Jinzhu Li , Sheng Zhao , Jinyu Li , Naoyuki Kanda

There are two types of methods for non-autoregressive text-to-speech models to learn the one-to-many relationship between text and speech effectively. The first one is to use an advanced generative framework such as normalizing flow (NF).…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-28 Yoonhyung Lee , Jinhyeok Yang , Kyomin Jung

Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models. Despite its advantageous properties, prior methods…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Quan Dao , Hao Phung , Binh Nguyen , Anh Tran

Classifier-free guidance (CFG) has become an essential component of modern diffusion models to enhance both generation quality and alignment with input conditions. However, CFG requires specific training procedures and is limited to…

Graphics · Computer Science 2025-11-06 Javad Rajabi , Soroush Mehraban , Seyedmorteza Sadat , Babak Taati

This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG). Our innovative approach transcends the standard modeling of solely data…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Zhicong Tang , Jianmin Bao , Dong Chen , Baining Guo

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.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-30 Sewade Ogun , Vincent Colotte , Emmanuel Vincent

Speech enhancement involves the distinction of a target speech signal from an intrusive background. Although generative approaches using Variational Autoencoders or Generative Adversarial Networks (GANs) have increasingly been used in…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-17 Martin Strauss , Bernd Edler

Recent advances in Text-to-Speech (TTS) have enabled highly natural speech synthesis, yet integrating speech with complex background environments remains challenging. We introduce UmbraTTS, a flow-matching based TTS model that jointly…