# Interpolating Speaker Identities in Embedding Space for Data Expansion

arXiv: https://arxiv.org/abs/2508.19210 · HTML: https://mlsanity.com/paper/2508.19210/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Builds on (most cited first, 24 of 24)

- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [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)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit](https://mlsanity.com/paper/2210.17016/) (2022)
- [SynthASR: Unlocking Synthetic Data for Speech Recognition](https://mlsanity.com/paper/2106.07803/) (2021)
- [Reshape Dimensions Network for Speaker Recognition](https://mlsanity.com/paper/2407.18223/) (2024)
- [VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark](https://mlsanity.com/paper/2407.11510/) (2024)
- [The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021](https://mlsanity.com/paper/2109.01989/) (2021)
- [3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement](https://mlsanity.com/paper/2306.15354/) (2023)
- [Self-supervised Speaker Recognition with Loss-gated Learning](https://mlsanity.com/paper/2110.03869/) (2021)
- [Disentangling Voice and Content with Self-Supervision for Speaker Recognition](https://mlsanity.com/paper/2310.01128/) (2023)
- [MFA: TDNN with Multi-scale Frequency-channel Attention for Text-independent Speaker Verification with Short Utterances](https://mlsanity.com/paper/2202.01624/) (2022)
- [Xi-Vector Embedding for Speaker Recognition](https://mlsanity.com/paper/2108.05679/) (2021)
- [Golden Gemini is All You Need: Finding the Sweet Spots for Speaker Verification](https://mlsanity.com/paper/2312.03620/) (2023)
- [Overview of Speaker Modeling and Its Applications: From the Lens of Deep Speaker Representation Learning](https://mlsanity.com/paper/2407.15188/) (2024)
- [Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing](https://mlsanity.com/paper/2409.08346/) (2024)
- [SynVox2: Towards a privacy-friendly VoxCeleb2 dataset](https://mlsanity.com/paper/2309.06141/) (2023)
- [CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification](https://mlsanity.com/paper/2409.15234/) (2024)
- [Deep Normalization for Speaker Vectors](https://mlsanity.com/paper/2004.04095/) (2020)
- [Voice Conversion Augmentation for Speaker Recognition on Defective Datasets](https://mlsanity.com/paper/2404.00863/) (2024)
- [Libri2Vox Dataset: Target Speaker Extraction with Diverse Speaker Conditions and Synthetic Data](https://mlsanity.com/paper/2412.12512/) (2024)
- [Pushing the Frontiers of Self-Distillation Prototypes Network with Dimension Regularization and Score Normalization](https://mlsanity.com/paper/2505.13826/) (2025)

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

- [EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis](https://mlsanity.com/paper/2608.23791/) (2026)

## Abstract (arXiv)

The success of deep learning-based speaker verification systems is largely attributed to access to large-scale and diverse speaker identity data. However, collecting data from more identities is expensive, challenging, and often limited by privacy concerns. To address this limitation, we propose INSIDE (Interpolating Speaker Identities in Embedding Space), a novel data expansion method that synthesizes new speaker identities by interpolating between existing speaker embeddings. Specifically, we select pairs of nearby speaker embeddings from a pretrained speaker embedding space and compute intermediate embeddings using spherical linear interpolation. These interpolated embeddings are then fed to a text-to-speech system to generate corresponding speech waveforms. The resulting data is combined with the original dataset to train downstream models. Experiments show that models trained with INSIDE-expanded data outperform those trained only on real data, achieving 3.06% to 5.24% relative improvements. While INSIDE is primarily designed for speaker verification, we also validate its effectiveness on gender classification, where it yields a 13.44% relative improvement. Moreover, INSIDE is compatible with other augmentation techniques and can serve as a flexible, scalable addition to existing training pipelines.