# Fine-Grained and Interpretable Neural Speech Editing

arXiv: https://arxiv.org/abs/2407.05471 · HTML: https://mlsanity.com/paper/2407.05471/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2024.

## Built on by (most cited first, 6 of 6)

- [Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces](https://mlsanity.com/paper/2603.12642/) (2026)
- [Coherent Audio-Visual Editing via Conditional Audio Generation Following Video Edits](https://mlsanity.com/paper/2512.07209/) (2025)
- [Neural Speech Extraction with Human Feedback](https://mlsanity.com/paper/2508.03041/) (2025)
- [PitchFlower: A flow-based neural audio codec with pitch controllability](https://mlsanity.com/paper/2510.25566/) (2025)
- [Pseudo-Cepstrum: Pitch Modification for Mel-Based Neural Vocoders](https://mlsanity.com/paper/2512.16519/) (2025)
- [Latent Fourier Transform](https://mlsanity.com/paper/2604.17986/) (2026)

## Abstract (arXiv)

Fine-grained editing of speech attributesunicodex2014such as prosody (i.e., the pitch, loudness, and phoneme durations), pronunciation, speaker identity, and formantsunicodex2014is useful for fine-tuning and fixing imperfections in human and AI-generated speech recordings for creation of podcasts, film dialogue, and video game dialogue. Existing speech synthesis systems use representations that entangle two or more of these attributes, prohibiting their use in fine-grained, disentangled editing. In this paper, we demonstrate the first disentangled and interpretable representation of speech with comparable subjective and objective vocoding reconstruction accuracy to Mel spectrograms. Our interpretable representation, combined with our proposed data augmentation method, enables training an existing neural vocoder to perform fast, accurate, and high-quality editing of pitch, duration, volume, timbral correlates of volume, pronunciation, speaker identity, and spectral balance.