mlsanityData to 14 Oct 2026

FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis

arXiv 2106.15123 ↗First posted 29 Jun 2021eess.AS cs.LG cs.SDcited by 12

Not on the map. Why?

Abstract (arXiv)

Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models. Prosodic speech can be generated by conditioning acoustic features. However, synthesized speech with a large pitch-shift scale suffers from audio quality degradation, and speaker characteristics deformation. To address this problem, we propose a feed-forward Transformer based TTS model that is designed based on the source-filter theory. This model, called FastPitchFormant, has a unique structure that handles text and acoustic features in parallel. With modeling each feature separately, the tendency that the model learns the relationship between two features can be mitigated.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 19 of its 28 references that are in the map. First posted on arXiv 29 Jun 2021.

Builds on

19 of 28 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018Self-Attention with Relative Position Representationscited by 1,120
  3. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  4. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
  5. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 490
  6. 2018Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesiscited by 259
  7. 2018Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotroncited by 173
  8. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 151
  9. 2018Hierarchical Generative Modeling for Controllable Speech Synthesiscited by 93
  10. 2018Learning latent representations for style control and transfer in end-to-end speech synthesiscited by 61
  11. 2020Parallel Tacotron: Non-Autoregressive and Controllable TTScited by 49
  12. 2018Robust and fine-grained prosody control of end-to-end speech synthesiscited by 48
7 more
  1. 2020Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesiscited by 41
  2. 2020Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody priorcited by 33
  3. 2020VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Networkcited by 26
  4. 2018Neural source-filter-based waveform model for statistical parametric speech synthesiscited by 22
  5. 2019Adversarially Trained End-to-end Korean Singing Voice Synthesis Systemcited by 22
  6. 2019Disentangling Timbre and Singing Style with Multi-singer Singing Synthesis Systemcited by 2
  7. 2020Knowledge-and-Data-Driven Amplitude Spectrum Prediction for Hierarchical Neural Vocoderscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 6; 2023: 3; 2024: 2; 2025: 1.

12 papers.

  1. 2022PromptTTS: Controllable Text-to-Speech with Text Descriptionscited by 110
  2. 2023TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Modelscited by 48
  3. 2023PromptTTS 2: Describing and Generating Voices with Text Promptcited by 48
  4. 2022Heterogeneous Target Speech Separationcited by 13
  5. 2023PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTScited by 4
  6. 2022Controllable speech synthesis by learning discrete phoneme-level prosodic representationscited by 3
  7. 2022Controllable Accented Text-to-Speech Synthesiscited by 2
  8. 2022Enhancement of Pitch Controllability using Timbre-Preserving Pitch Augmentation in FastPitchcited by 1
  9. 2024MultiVerse: Efficient and Expressive Zero-Shot Multi-Task Text-to-Speechcited by 1
  10. 2025RESOUND: Speech Reconstruction from Silent Videos via Acoustic-Semantic Decomposed Modelingcited by 1
  11. 2022SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speechcited by 0
  12. 2024Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generationcited by 0