DurIAN-E: Duration Informed Attention Network For Expressive Text-to-Speech Synthesis
On the map: Diffusion models → Audio, speech and music
Abstract (arXiv)
This paper introduces an improved duration informed attention neural network (DurIAN-E) for expressive and high-fidelity text-to-speech (TTS) synthesis. Inherited from the original DurIAN model, an auto-regressive model structure in which the alignments between the input linguistic information and the output acoustic features are inferred from a duration model is adopted. Meanwhile the proposed DurIAN-E utilizes multiple stacked SwishRNN-based Transformer blocks as linguistic encoders. Style-Adaptive Instance Normalization (SAIN) layers are exploited into frame-level encoders to improve the modeling ability of expressiveness. A denoiser incorporating both denoising diffusion probabilistic model (DDPM) for mel-spectrograms and SAIN modules is conducted to further improve the synthetic speech quality and expressiveness. Experimental results prove that the proposed expressive TTS model in this paper can achieve better performance than the state-of-the-art approaches in both subjective mean opinion score (MOS) and preference tests.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 18 of its 20 references that are in the map. First posted on arXiv 22 Sep 2023.
Builds on
18 of 20 references.
Closest ancestors · 2
Same direction, newest first
- 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speech3 Apr
- 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep
Other references · 16
- 2017Attention Is All You Needcited by 60,361
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
- 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
- 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
- 2018Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesiscited by 259
- 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 251
- 2018Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotroncited by 173
- 2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
- 2021Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generationcited by 93
- 2022StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesiscited by 33
- 2021Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modelingcited by 31
4 more
- 2019Exploring Transfer Learning for Low Resource Emotional TTScited by 21
- 2019Visualization and Interpretation of Latent Spaces for Controlling Expressive Speech Synthesis through Audio Analysiscited by 8
- 2021Meta-Voice: Fast few-shot style transfer for expressive voice cloning using meta learningcited by 5
- 2022Simple Recurrence Improves Masked Language Modelscited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2023EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
- 2022DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
- 2022NoreSpeech: Knowledge Distillation based Conditional Diffusion Model for Noise-robust Expressive TTS
- 2025FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis
- 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
- 2026DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis
- 2023NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
- 2023High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models