Short-Utterance Embedding Enhancement Method Based on Time Series Forecasting Technique for Text-Independent Speaker Verification
- Authors
- Choi, Jeong-Hwan; Yang, Joon-Young; Chang, Joon-Hyuk
- Issue Date
- Feb-2022
- Publisher
- IEEE
- Keywords
- short-duration speaker verification; Text-independent speaker verification; time series forecasting model
- Citation
- 2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Proceedings, pp.130 - 137
- Indexed
- SCOPUS
- Journal Title
- 2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Proceedings
- Start Page
- 130
- End Page
- 137
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/139507
- DOI
- 10.1109/ASRU51503.2021.9688156
- Abstract
- Short-utterance embedding, which is a speaker embedding extracted from a short utterance, shows poor speaker verification performance due to insufficient speaker information. To address the problem, we propose a method to map the set of short-utterance embeddings to a set of long-utterance embeddings based on a neural network. Specifically, a speech utterance is cropped into multiple segments whose durations are gradually increasing, and the speaker embeddings are extracted from the sequence of cropped segments using a pre-trained speaker embedding extractor. Subsequently, the sequence of embeddings is divided into a group of short-utterances embeddings and that of long-utterance embeddings. In our method, a sequence-to-sequence model based forecasting technique is employed, where an encoder transforms the group of short-utterance embeddings to a fixed-dimensional vector, and then a decoder converts the vector into a group of long-utterance embeddings. Experimental results on the VoxCeleb and Speakers in the Wild datasets show that our method improves the text-independent speaker verification performance under short utterance condition.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/139507)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.