Shi, Y., Huang, Q. and Hain, T. orcid.org/0000-0003-0939-3464 (2020) Weakly supervised training of hierarchical attention networks for speaker identification. In: Meng, H., Xu, B. and Zheng, T., (eds.) Proceedings of Interspeech 2020. Interspeech 2020, 25-29 Oct 2020, Shanghai, China. ISCA - International Speech Communication Association , pp. 2992-2996.
Abstract
Identifying multiple speakers without knowing where a speaker’s voice is in a recording is a challenging task. In this paper, a hierarchical attention network is proposed to solve a weakly labelled speaker identification problem. The use of a hierarchical structure, consisting of a frame-level encoder and a segment-level encoder, aims to learn speaker related information locally and globally. Speech streams are segmented into fragments. The frame-level encoder with attention learns features and highlights the target related frames locally, and output a fragment based embedding. The segment-level encoder works with a second attention layer to emphasize the fragments probably related to target speakers. The global information is finally collected from segment-level module to predict speakers via a classifier. To evaluate the effectiveness of the proposed approach, artificial datasets based on Switchboard Cellular part1 (SWBC) and Voxceleb1 are constructed in two conditions, where speakers’ voices are overlapped and not overlapped. Comparing to two baselines the obtained results show that the proposed approach can achieve better performances. Moreover, further experiments are conducted to evaluate the impact of utterance segmentation. The results show that a reasonable segmentation can slightly improve identification performances.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2020 ISCA. This is an author-produced version of a paper subsequently published in Proceedings of Interspeech 2020. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Weakly Supervised Learning; Speaker Identification; Hierarchical Attention; X-vectors; Attention Mechanism |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 15 Jul 2022 08:12 |
Last Modified: | 18 Jul 2022 15:40 |
Status: | Published |
Publisher: | ISCA - International Speech Communication Association |
Refereed: | Yes |
Identification Number: | 10.21437/interspeech.2020-1774 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:189095 |