# Beyond Cross-Reconstruction: Probing-Based Disentanglement Evaluation for Acoustic Teleportation Codecs

arXiv: https://arxiv.org/abs/2606.31365 · HTML: https://mlsanity.com/paper/2606.31365/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Vocoders and speech synthesis, one of 11 directions in Speech and audio language models.
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Placed in

- Speech and audio language models / [Vocoders and speech synthesis](https://mlsanity.com/speech/vocoders-and-speech-synthesis/)

## Builds on (most cited first, 13 of 13)

- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)
- [NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models](https://mlsanity.com/paper/2403.03100/) (2024)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [ICASSP 2023 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2303.11510/) (2023)
- [One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization](https://mlsanity.com/paper/1904.05742/) (2019)
- [ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers](https://mlsanity.com/paper/2204.09224/) (2022)
- [SCOREQ: Speech Quality Assessment with Contrastive Regression](https://mlsanity.com/paper/2410.06675/) (2024)
- [Learning Source Disentanglement in Neural Audio Codec](https://mlsanity.com/paper/2409.11228/) (2024)
- [FreeCodec: A disentangled neural speech codec with fewer tokens](https://mlsanity.com/paper/2412.01053/) (2024)
- [Disentangling speech from surroundings with neural embeddings](https://mlsanity.com/paper/2203.15578/) (2022)
- [Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks](https://mlsanity.com/paper/2505.06224/) (2025)
- [Acoustic Teleportation via Disentangled Neural Audio Codec Representations](https://mlsanity.com/paper/2510.13221/) (2025)

## Abstract (arXiv)

Some neural audio codecs disentangle speech into latent subspaces encoding content, speaker identity, and acoustics, enabling acoustic teleportation and voice conversion. Existing evaluations rely on cross-reconstruction quality, which cannot reliably detect leakage across partitions. We extend a probing based framework to assess disentanglement by regressing room-acoustic parameters (reverberation time, clarity, and direct-to-reverberant ratio) and classifying speaker identity, using the gap between intended and unintended partitions as the disentanglement measure. Applied to an acoustic teleportation codec, we find speaker identity is largely confined to its partition, while acoustics leak into the speech embeddings due to the training objective. Acoustic embeddings blindly estimate room parameters within 0.02 s of supervised baselines, indicating physically meaningful structure emerges without explicit supervision.