# MIRNet: Learning multiple identities representations in overlapped speech

arXiv: https://arxiv.org/abs/2008.01698 · HTML: https://mlsanity.com/paper/2008.01698/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 3 of 3)

- [SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device](https://mlsanity.com/paper/2308.08137/) (2023)
- [Attention based Broadly Self-guided Network for Low light Image Enhancement](https://mlsanity.com/paper/2112.06226/) (2021)
- [LoLiSRFlow: Joint Single Image Low-light Enhancement and Super-resolution via Cross-scale Transformer-based Conditional Flow](https://mlsanity.com/paper/2402.18871/) (2024)

## Abstract (arXiv)

Many approaches can derive information about a single speaker's identity from the speech by learning to recognize consistent characteristics of acoustic parameters. However, it is challenging to determine identity information when there are multiple concurrent speakers in a given signal. In this paper, we propose a novel deep speaker representation strategy that can reliably extract multiple speaker identities from an overlapped speech. We design a network that can extract a high-level embedding that contains information about each speaker's identity from a given mixture. Unlike conventional approaches that need reference acoustic features for training, our proposed algorithm only requires the speaker identity labels of the overlapped speech segments. We demonstrate the effectiveness and usefulness of our algorithm in a speaker verification task and a speech separation system conditioned on the target speaker embeddings obtained through the proposed method.