# Reshape Dimensions Network for Speaker Recognition

arXiv: https://arxiv.org/abs/2407.18223 · HTML: https://mlsanity.com/paper/2407.18223/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2024.

## Built on by (most cited first, 28 of 28)

- [SVeritas: Benchmark for Robust Speaker Verification under Diverse Conditions](https://mlsanity.com/paper/2509.17091/) (2025)
- [VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency](https://mlsanity.com/paper/2509.15969/) (2025)
- [Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and Conditional Flow Matching](https://mlsanity.com/paper/2411.02026/) (2024)
- [Aligning Generative Speech Enhancement with Perceptual Feedback](https://mlsanity.com/paper/2507.09929/) (2025)
- [IDFace: Face Template Protection for Efficient and Secure Identification](https://mlsanity.com/paper/2507.12050/) (2025)
- [Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruning](https://mlsanity.com/paper/2510.04213/) (2025)
- [VoXtream2: Full-stream TTS with dynamic speaking rate control](https://mlsanity.com/paper/2603.13518/) (2026)
- [LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention](https://mlsanity.com/paper/2506.02083/) (2025)
- [Scores Know Bobs Voice: Speaker Impersonation Attack](https://mlsanity.com/paper/2603.02781/) (2026)
- [Interpolating Speaker Identities in Embedding Space for Data Expansion](https://mlsanity.com/paper/2508.19210/) (2025)
- [Provable Speech Attributes Conversion via Latent Independence](https://mlsanity.com/paper/2510.05191/) (2025)
- [DELULU: Discriminative Embedding Learning Using Latent Units for Speaker-Aware Self-Trained Speech Foundational Model](https://mlsanity.com/paper/2510.17662/) (2025)
- [Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning](https://mlsanity.com/paper/2603.21875/) (2026)
- [What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification](https://mlsanity.com/paper/2603.24432/) (2026)
- [Performance and Complexity Trade-off Optimization of Speech Models During Training](https://mlsanity.com/paper/2601.13704/) (2026)
- [Triage knowledge distillation for speaker verification](https://mlsanity.com/paper/2601.14699/) (2026)
- [DFKI-Speech System for WildSpoof Challenge: A robust framework for SASV In-the-Wild](https://mlsanity.com/paper/2602.02286/) (2026)
- [Tagarela - A Portuguese speech dataset from podcasts](https://mlsanity.com/paper/2603.15326/) (2026)
- [Enhancing Speaker Verification with Whispered Speech via Post-Processing](https://mlsanity.com/paper/2604.20229/) (2026)
- [CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding](https://mlsanity.com/paper/2606.04418/) (2026)
- [On Low-Bit Quantization Errors in Speaker Verification: Diagnostic and Mitigation](https://mlsanity.com/paper/2606.08078/) (2026)
- [From A to B to A: Palindromic Zero-Shot Voice Conversion with Non-Parallel Data](https://mlsanity.com/paper/2606.08843/) (2026)
- [Kiwano: A Cutting-Edge Open-Source Toolkit for Speaker Verification](https://mlsanity.com/paper/2606.22369/) (2026)
- [ZONOS2 Technical Report](https://mlsanity.com/paper/2606.24320/) (2026)
- [MECT: Mixture of Experts with CNN-Transformer Network for Speaker verification](https://mlsanity.com/paper/2609.24061/) (2026)
- [CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification](https://mlsanity.com/paper/2609.33212/) (2026)
- [InterBias-SV: Compound Conditions in Speaker Verification](https://mlsanity.com/paper/2609.36500/) (2026)
- [FASTDIAR: Frame-level speaker encoder for Streaming Diarization](https://mlsanity.com/paper/2610.02941/) (2026)

## Abstract (arXiv)

In this paper, we present Reshape Dimensions Network (ReDimNet), a novel neural network architecture for extracting utterance-level speaker representations. Our approach leverages dimensionality reshaping of 2D feature maps to 1D signal representation and vice versa, enabling the joint usage of 1D and 2D blocks. We propose an original network topology that preserves the volume of channel-timestep-frequency outputs of 1D and 2D blocks, facilitating efficient residual feature maps aggregation. Moreover, ReDimNet is efficiently scalable, and we introduce a range of model sizes, varying from 1 to 15 M parameters and from 0.5 to 20 GMACs. Our experimental results demonstrate that ReDimNet achieves state-of-the-art performance in speaker recognition while reducing computational complexity and the number of model parameters.