# Residual Tokens Enhance Masked Autoencoders for Speech Modeling

arXiv: https://arxiv.org/abs/2601.19399 · HTML: https://mlsanity.com/paper/2601.19399/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Builds on (most cited first, 28 of 28)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://mlsanity.com/paper/1803.09017/) (2018)
- [Speech Resynthesis from Discrete Disentangled Self-Supervised Representations](https://mlsanity.com/paper/2104.00355/) (2021)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss](https://mlsanity.com/paper/1905.05879/) (2019)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement](https://mlsanity.com/paper/2008.00264/) (2020)
- [Spirit LM: Interleaved Spoken and Written Language Model](https://mlsanity.com/paper/2402.05755/) (2024)
- [CREPE: A Convolutional Representation for Pitch Estimation](https://mlsanity.com/paper/1802.06182/) (2018)
- [Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data](https://mlsanity.com/paper/1709.07902/) (2017)
- [Hierarchical Generative Modeling for Controllable Speech Synthesis](https://mlsanity.com/paper/1810.07217/) (2018)
- [VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion](https://mlsanity.com/paper/2106.10132/) (2021)
- [The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems](https://mlsanity.com/paper/1806.09514/) (2018)
- [TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio](https://mlsanity.com/paper/2304.01448/) (2023)
- [SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics](https://mlsanity.com/paper/2401.16812/) (2024)
- [StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion](https://mlsanity.com/paper/1907.12279/) (2019)
- [High-Fidelity Neural Phonetic Posteriorgrams](https://mlsanity.com/paper/2402.17735/) (2024)
- [AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder](https://mlsanity.com/paper/2501.05332/) (2025)

## Built on by (most cited first, 1 of 1)

- [HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models](https://mlsanity.com/paper/2606.27627/) (2026)

## Abstract (arXiv)

Recent speech modeling relies on explicit attributes such as pitch, content, and speaker identity, but these alone cannot capture the full richness of natural speech. We introduce RT-MAE, a novel masked autoencoder framework that augments the supervised attributes-based modeling with unsupervised residual trainable tokens, designed to encode the information not explained by explicit labeled factors (e.g., timbre variations, noise, emotion etc). Experiments show that RT-MAE improves reconstruction quality, preserving content and speaker similarity while enhancing expressivity. We further demonstrate its applicability to speech enhancement, removing noise at inference while maintaining controllability and naturalness.