In this paper, we propose an effective training strategy to extract robust speaker representations from a speech signal. One of the key challenges in speaker recognition tasks is to learn latent representations or embeddings containing solely speaker characteristic information in order to be robust in terms of intraspeaker variations. By modifying the network architecture to generate both speaker-related and speaker-unrelated representations, we exploit a learning criterion which minimizes the mutual information between these disentangled embeddings. We also introduce an identity change loss criterion which utilizes a reconstruction error to different utterances spoken by the same speaker. Since the proposed criteria reduce the variation of speaker characteristics caused by changes in background environment or spoken content, the resulting embeddings of each speaker become more consistent. The effectiveness of the proposed method is demonstrated through two tasks; disentanglement performance, and improvement of speaker recognition accuracy compared to the baseline model on a benchmark dataset, VoxCeleb1. Ablation studies also show the impact of each criterion on overall performance.
In this letter, a generic search grid generation algorithm for far-field source localization (SL) is proposed. Since conventional uniform regular grid structures only consider the resolution of the distribution, it is difficult to control the number of grid points to be distributed. The proposed algorithm generates a search grid by distributing a desired number of points evenly, depending on the target criterion, in either direction of arrival or time difference of arrival domain. The experimental results show that the proposed algorithm provides optimally distributed grid points given the number of desired points and the corresponding domain for SL processing.
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 highlevel 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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.