# Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

arXiv: https://arxiv.org/abs/2104.00355 · HTML: https://mlsanity.com/paper/2104.00355/

## Key facts

- Cited by 243 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 52 references that are in the map.
- First posted on arXiv 1 Apr 2021.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [LPCNet: Improving Neural Speech Synthesis Through Linear Prediction](https://mlsanity.com/paper/1810.11846/) (2018)
- [Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data](https://mlsanity.com/paper/1709.07902/) (2017)
- [Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge](https://mlsanity.com/paper/2005.09409/) (2020)
- [End-to-End Text-Dependent Speaker Verification](https://mlsanity.com/paper/1509.08062/) (2015)
- [Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder](https://mlsanity.com/paper/1910.06464/) (2019)
- [Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation](https://mlsanity.com/paper/2007.13465/) (2020)
- [The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units](https://mlsanity.com/paper/2010.05967/) (2020)
- [The Zero Resource Speech Challenge 2019: TTS without T](https://mlsanity.com/paper/1904.11469/) (2019)
- [Wavenet based low rate speech coding](https://mlsanity.com/paper/1712.01120/) (2017)
- [Unsupervised Cross-Domain Singing Voice Conversion](https://mlsanity.com/paper/2008.02830/) (2020)
- [Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge](https://mlsanity.com/paper/2005.11676/) (2020)
- [Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks](https://mlsanity.com/paper/1904.07556/) (2019)
- [A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet](https://mlsanity.com/paper/1903.12087/) (2019)
- [TTS Skins: Speaker Conversion via ASR](https://mlsanity.com/paper/1904.08983/) (2019)
- [High Fidelity Speech Regeneration with Application to Speech Enhancement](https://mlsanity.com/paper/2102.00429/) (2021)
- [Improving Opus Low Bit Rate Quality with Neural Speech Synthesis](https://mlsanity.com/paper/1905.04628/) (2019)

## Built on by (most cited first, 30 of 243)

- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [AudioGen: Textually Guided Audio Generation](https://mlsanity.com/paper/2209.15352/) (2022)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models](https://mlsanity.com/paper/2403.03100/) (2024)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [Direct speech-to-speech translation with discrete units](https://mlsanity.com/paper/2107.05604/) (2021)
- [Generative Spoken Dialogue Language Modeling](https://mlsanity.com/paper/2203.16502/) (2022)
- [Spirit LM: Interleaved Spoken and Written Language Model](https://mlsanity.com/paper/2402.05755/) (2024)
- [Textless Speech-to-Speech Translation on Real Data](https://mlsanity.com/paper/2112.08352/) (2021)
- [Text-Free Prosody-Aware Generative Spoken Language Modeling](https://mlsanity.com/paper/2109.03264/) (2021)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [Textually Pretrained Speech Language Models](https://mlsanity.com/paper/2305.13009/) (2023)
- [EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis](https://mlsanity.com/paper/2308.05725/) (2023)
- [WavChat: A Survey of Spoken Dialogue Models](https://mlsanity.com/paper/2411.13577/) (2024)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)
- [Recent Advances in Speech Language Models: A Survey](https://mlsanity.com/paper/2410.03751/) (2024)
- [Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations](https://mlsanity.com/paper/2110.14513/) (2021)
- [ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers](https://mlsanity.com/paper/2204.09224/) (2022)
- [General-purpose, long-context autoregressive modeling with Perceiver AR](https://mlsanity.com/paper/2202.07765/) (2022)
- [UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units](https://mlsanity.com/paper/2212.08055/) (2022)
- [Generative Pre-training for Speech with Flow Matching](https://mlsanity.com/paper/2310.16338/) (2023)
- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [Masked Audio Generation using a Single Non-Autoregressive Transformer](https://mlsanity.com/paper/2401.04577/) (2024)
- [Towards Robust Speech Representation Learning for Thousands of Languages](https://mlsanity.com/paper/2407.00837/) (2024)

## Abstract (arXiv)

We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This allows to synthesize speech in a controllable manner. We analyze various state-of-the-art, self-supervised representation learning methods and shed light on the advantages of each method while considering reconstruction quality and disentanglement properties. Specifically, we evaluate the F0 reconstruction, speaker identification performance (for both resynthesis and voice conversion), recordings' intelligibility, and overall quality using subjective human evaluation. Lastly, we demonstrate how these representations can be used for an ultra-lightweight speech codec. Using the obtained representations, we can get to a rate of 365 bits per second while providing better speech quality than the baseline methods. Audio samples can be found under the following link: speechbot.github.io/resynthesis.