# Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations

arXiv: https://arxiv.org/abs/1906.10508 · HTML: https://mlsanity.com/paper/1906.10508/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2019.

## Built on by (most cited first, 23 of 23)

- [Emotional Voice Conversion: Theory, Databases and ESD](https://mlsanity.com/paper/2105.14762/) (2021)
- [Emotion Intensity and its Control for Emotional Voice Conversion](https://mlsanity.com/paper/2201.03967/) (2022)
- [Speech Synthesis with Mixed Emotions](https://mlsanity.com/paper/2208.05890/) (2022)
- [MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames](https://mlsanity.com/paper/2102.12841/) (2021)
- [Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training](https://mlsanity.com/paper/2103.16809/) (2021)
- [SpeechNet: A Universal Modularized Model for Speech Processing Tasks](https://mlsanity.com/paper/2105.03070/) (2021)
- [DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training](https://mlsanity.com/paper/2307.16549/) (2023)
- [Disentangling Voice and Content with Self-Supervision for Speaker Recognition](https://mlsanity.com/paper/2310.01128/) (2023)
- [Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion](https://mlsanity.com/paper/2203.12813/) (2022)
- [A Comparative Study of Self-supervised Speech Representation Based Voice Conversion](https://mlsanity.com/paper/2207.04356/) (2022)
- [Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment](https://mlsanity.com/paper/2309.09470/) (2023)
- [Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing](https://mlsanity.com/paper/2211.01522/) (2022)
- [How Deep Are the Fakes? Focusing on Audio Deepfake: A Survey](https://mlsanity.com/paper/2111.14203/) (2021)
- [Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation](https://mlsanity.com/paper/2508.16332/) (2025)
- [RW-Resnet: A Novel Speech Anti-Spoofing Model Using Raw Waveform](https://mlsanity.com/paper/2108.05684/) (2021)
- [Speak Like a Dog: Human to Non-human creature Voice Conversion](https://mlsanity.com/paper/2206.04780/) (2022)
- [Reimagining Speech: A Scoping Review of Deep Learning-Powered Voice Conversion](https://mlsanity.com/paper/2311.08104/) (2023)
- [Appearance Debiased Gaze Estimation via Stochastic Subject-Wise Adversarial Learning](https://mlsanity.com/paper/2401.13865/) (2024)
- [Non-Parallel Voice Conversion for ASR Augmentation](https://mlsanity.com/paper/2209.06987/) (2022)
- [MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora](https://mlsanity.com/paper/2604.11552/) (2026)
- [Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations](https://mlsanity.com/paper/2107.12346/) (2021)
- [Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition](https://mlsanity.com/paper/2402.14523/) (2024)
- [MF-Speech: Achieving Fine-Grained and Compositional Control in Speech Generation via Factor Disentanglement](https://mlsanity.com/paper/2511.12074/) (2025)

## Abstract (arXiv)

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion is achieved by preserving the linguistic representations of source utterances while replacing the speaker representations with the target ones. Our model is built under the framework of encoder-decoder neural networks. A recognition encoder is designed to learn the disentangled linguistic representations with two strategies. First, phoneme transcriptions of training data are introduced to provide the references for leaning linguistic representations of audio signals. Second, an adversarial training strategy is employed to further wipe out speaker information from the linguistic representations. Meanwhile, speaker representations are extracted from audio signals by a speaker encoder. The model parameters are estimated by two-stage training, including a pretraining stage using a multi-speaker dataset and a fine-tuning stage using the dataset of a specific conversion pair. Since both the recognition encoder and the decoder for recovering acoustic features are seq2seq neural networks, there are no constrains of frame alignment and frame-by-frame conversion in our proposed method. Experimental results showed that our method obtained higher similarity and naturalness than the best non-parallel voice conversion method in Voice Conversion Challenge 2018. Besides, the performance of our proposed method was closed to the state-of-the-art parallel seq2seq voice conversion method.