MIRNet: Learning multiple identities representations in overlapped speech

Abstract

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.

arXiv commentAccepted in Interspeech 2020

References in corpus (7)

• VoxCeleb2: Deep Speaker Recognition
• A Structured Self-attentive Sentence Embedding
• Deep Speaker: an End-to-End Neural Speaker Embedding System
• In defence of metric learning for speaker recognition
• Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances
• Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs
• Supervised Speaker Embedding De-Mixing in Two-Speaker Environment

Cited by in corpus (1)

• Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs