# LISE : Listenable Interpretable Speaker Embeddings

arXiv: https://arxiv.org/abs/2606.21305 · HTML: https://mlsanity.com/paper/2606.21305/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 15 of 15)

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [SPINE: SParse Interpretable Neural Embeddings](https://mlsanity.com/paper/1711.08792/) (2017)
- [MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification](https://mlsanity.com/paper/2203.15249/) (2022)
- [Route Sparse Autoencoder to Interpret Large Language Models](https://mlsanity.com/paper/2503.08200/) (2025)
- [Bias in Automated Speaker Recognition](https://mlsanity.com/paper/2201.09486/) (2022)
- [Explainable Attribute-Based Speaker Verification](https://mlsanity.com/paper/2405.19796/) (2024)
- [Leveraging speaker attribute information using multi task learning for speaker verification and diarization](https://mlsanity.com/paper/2010.14269/) (2020)
- [Objective Measurements of Voice Quality](https://mlsanity.com/paper/2410.09578/) (2024)
- [Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions](https://mlsanity.com/paper/2310.17502/) (2023)
- [Vo-Ve: An Explainable Voice-Vector for Speaker Identity Evaluation](https://mlsanity.com/paper/2506.19446/) (2025)
- [Interpreting the Dimensions of Speaker Embedding Space](https://mlsanity.com/paper/2510.16489/) (2025)

## Abstract (arXiv)

Deep neural network-based automatic speaker verification (ASV) systems achieve impressive performance but their embedding representations remain opaque, lacking a structured and perceptually verifiable explanation of the vocal characteristics they encode. Existing approaches either require annotation of speaker attributes or introduce alternative representations whose interpretability is unvalidated with listeners. We propose Listenable Interpretable Speaker Embeddings (LISE), a label-free framework that decomposes pretrained speaker embeddings into a small set of components. This decomposition yields a structured representation that supports the analysis of what information has been encoded by speaker embeddings. LISE preserves ASV performance with negligible EER degradation on x-vector and ECAPA-TDNN. Crucially, the interpretability of these components for human listeners is demonstrated through listening experiments, where participants distinguished speakers with 83.9% accuracy.