Data to 7 Oct 2026

Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling

arXiv 2010.04301 ↗First posted 8 Oct 2020cs.SD cs.CLcited by 65

Not on the map. Why?

Abstract (arXiv)

This paper presents Non-Attentive Tacotron based on the Tacotron 2 text-to-speech model, replacing the attention mechanism with an explicit duration predictor. This improves robustness significantly as measured by unaligned duration ratio and word deletion rate, two metrics introduced in this paper for large-scale robustness evaluation using a pre-trained speech recognition model. With the use of Gaussian upsampling, Non-Attentive Tacotron achieves a 5-scale mean opinion score for naturalness of 4.41, slightly outperforming Tacotron 2. The duration predictor enables both utterance-wide and per-phoneme control of duration at inference time. When accurate target durations are scarce or unavailable in the training data, we propose a method using a fine-grained variational auto-encoder to train the duration predictor in a semi-supervised or unsupervised manner, with results almost as good as supervised training.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 17; 2022: 18; 2023: 16; 2024: 12; 2025: 2.

65 papers.

Sort:

By area:

2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
2021A Survey on Neural Speech Synthesiscited by 182
2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
2023Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLMcited by 92
2022CVSS Corpus and Massively Multilingual Speech-to-Speech Translationcited by 71
2021Translatotron 2: High-quality direct speech-to-speech translation with voice preservationcited by 69
2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIcited by 68
2023SLM: Bridge the thin gap between speech and text foundation modelscited by 67
2021WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesiscited by 65
2022UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Unitscited by 60
2021PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTScited by 52
2023E3 TTS: Easy End-to-End Diffusion-based Text to Speechcited by 30

38 more

2024RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesiscited by 26
2023A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speechcited by 22
2023Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representationscited by 22
2022Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translationcited by 20
2022WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iterationcited by 20
2022SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesiscited by 18
2021Integrated Speech and Gesture Synthesiscited by 16
2021Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speechcited by 14
2024SSDM: Scalable Speech Dysfluency Modelingcited by 13
2021More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speechcited by 12
2023Translatotron 3: Speech to Speech Translation with Monolingual Datacited by 12
2022Residual Adapters for Few-Shot Text-to-Speech Speaker Adaptationcited by 10
2021Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architecturescited by 8
2021Neural HMMs are all you need (for high-quality attention-free TTS)cited by 8
2021Cross-lingual Low Resource Speaker Adaptation Using Phonological Featurescited by 8
2023Speak While You Think: Streaming Speech Synthesis During Text Generationcited by 8
2025SpeakStream: Streaming Text-to-Speech with Interleaved Datacited by 8
2021TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Predictioncited by 7
2023UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Modelcited by 7
2024DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Modelscited by 7
2021Review of end-to-end speech synthesis technology based on deep learningcited by 6
2021Word-Level Style Control for Expressive, Non-attentive Speech Synthesiscited by 5
2022Distribution augmentation for low-resource expressive text-to-speechcited by 5
2022A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesiscited by 5
2024Direct Speech-to-Speech Neural Machine Translation: A Surveycited by 5
2023On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognitioncited by 4
2024Creating an African American-Sounding TTS: Guidelines, Technical Challenges,and Surprising Evaluationscited by 4
2024On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architecturescited by 4
2024Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speechcited by 4
2025Voice Cloning: Comprehensive Surveycited by 4
2022Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciationcited by 3
2022Controllable speech synthesis by learning discrete phoneme-level prosodic representationscited by 3
2023Prosody Analysis of Audiobookscited by 3
2024On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognitioncited by 3
2021Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Datacited by 2
2022Self-supervised learning for robust voice cloningcited by 2
2022Fine-grained Noise Control for Multispeaker Speech Synthesiscited by 2
2022Non-Parallel Voice Conversion for ASR Augmentationcited by 2

50 most cited of 65 All 65 (JSON)