Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance

By Heeseung Kim, Sungwon Kim, Sungroh Yoon. 2021

140 citations recorded by the source corpus.

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 phoneme classifier for classifier guidance. Our unconditional diffusion model learns to generate speech without any context from untranscribed speech data. For TTS synthesis, we guide the generative process of the diffusion model with a phoneme classifier trained on a large-scale speech recognition dataset. We present a norm-based scaling method that reduces the pronunciation errors of classifier guidance in Guided-TTS. We show that Guided-TTS achieves a performance comparable to that of the state-of-the-art TTS model, Grad-TTS, without any transcript for LJSpeech. We further demonstrate that Guided-TTS performs well on diverse datasets including a long-form untranscribed dataset.

Subfields: Artificial Intelligence, Generative Models, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Rongjie Huang
2. Zhou Zhao
3. Jinglin Liu
4. Yi Ren
5. Ziyue Jiang
6. Xie Chen
7. Zhe Ye
8. Sung Ju Hwang

In Generative Models

1. Zhou Zhao
2. Yi Ren
3. Rongjie Huang
4. Jinglin Liu
5. Minki Kang
6. Zhuo Chen
7. Qiang Yang
8. Zhenhui Ye

In Speech & Audio

1. Jinglin Liu
2. Rongjie Huang
3. Zhou Zhao
4. Yi Ren
5. Xie Chen
6. Ziyue Jiang
7. Qiang Yang
8. Ziyang Ma

In Signal Processing

1. Jinglin Liu
2. Rongjie Huang
3. Zhou Zhao
4. Yi Ren
5. Ziyue Jiang
6. Xie Chen
7. Qiang Yang
8. Minki Kang

Citations in the corpus

• ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering (2024, methodology): “Some methods, utilizing techniques such as VAE (Hsu et al., 2019; Lee et al., 2022), flow (Miao et al., 2020; Kim et al., 2020), diffusion (Jeong et al., 2021; Kim et al., 2022; Popov et al., 2021), and others (Wu and Shi, 2022), have achieved promising performance in end-to-end speech synthesis.”
• Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias (2023, background): “Text-to-speech (TTS) synthesis [53, 2, 49, 35, 48, 45, 29, 66, 43, 28] aims to generate human-like speech from text and has gained significant attention in the field of machine learning.”
• Grad-StyleSpeech: Any-Speaker Adaptive Text-to-Speech Synthesis with Diffusion Models (2022, methodology): “Remarkably, diffusion models [5, 6] have recently been shown to synthesize high-quality images in the image generation tasks and speech in the TTS synthesis tasks [7, 8, 9].”
• HierSpeech++: Bridging the Gap Between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-Shot Speech Synthesis (2023, unknown): “The details are described in the following subsections.”
• DDGR: Continual Learning with Deep Diffusion-based Generative Replay (2023, background): “…have shown their exquisite potential in the field of computer vision (Dhariwal & Nichol, 2021; Ho et al., 2022b; Li et al., 2022; Luo & Hu, 2021), audio processing (Chen et al., 2021; Popov et al., 2021; Kim et al., 2022), and AI for science (Luo et al., 2021; Xu et al., 2022; Jing et al., 2022).”
• Mega-TTS 2: Zero-Shot Text-to-Speech with Arbitrary Length Speech Prompts (2023, background): “In recent years, there has been remarkable progress in the development of text-to-speech (TTS) technology (Shen et al., 2018; Li et al., 2019; Kim et al., 2020; Ren et al., 2019; 2020; Kim et al., 2021; 2022a; Lee et al., 2022).”