mlsanityData to 7 Oct 2026

AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment

arXiv 2003.01950 ↗First posted 4 Mar 2020eess.AS cs.CL cs.SDcited by 20

Not on the map. Why?

Abstract (arXiv)

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character is determined by a duration predictor.Instead of adopting the attention mechanism in Transformer TTS to align text to mel-spectrum, the alignment loss is presented to consider all possible alignments in training by use of dynamic programming. Experiments on the LJSpeech dataset show that our model achieves not only state-of-the-art performance which outperforms Transformer TTS by 0.03 in mean option score (MOS), but also a high efficiency which is more than 50 times faster than real-time.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 5; 2023: 1; 2024: 1; 2025: 3.

20 papers.

Sort:

By area:

  1. 2021A Survey on Neural Speech Synthesiscited by 182
  2. 2022DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANscited by 43
  3. 2021SpeechNet: A Universal Modularized Model for Speech Processing Taskscited by 16
  4. 2021Federated Learning with Dynamic Transformer for Text to Speechcited by 11
  5. 2021Neural HMMs are all you need (for high-quality attention-free TTS)cited by 8
  6. 2021Review of end-to-end speech synthesis technology based on deep learningcited by 6
  7. 2021Fast DCTTS: Efficient Deep Convolutional Text-to-Speechcited by 4
  8. 2022Regotron: Regularizing the Tacotron2 architecture via monotonic alignment losscited by 3
  9. 2025Marco-Voice Technical Reportcited by 3
  10. 2022Semi-Supervised Learning Based on Reference Model for Low-resource TTScited by 2
  11. 2021UniTTS: Residual Learning of Unified Embedding Space for Speech Style Controlcited by 1
  12. 2022Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speechcited by 1
8 more
  1. 2023Cross-Utterance Conditioned VAE for Speech Generationcited by 1
  2. 2024MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spacescited by 1
  3. 2025Eliminating stability hallucinations in llm-based tts models via attention guidancecited by 1
  4. 2025AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMscited by 1
  5. 2021Sprachsynthese -- State-of-the-Art in englischer und deutscher Sprachecited by 0
  6. 2021Multi-Scale Spectrogram Modelling for Neural Text-to-Speechcited by 0
  7. 2021PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Controlcited by 0
  8. 2022AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modelingcited by 0