Leveraging Speaker Embeddings with Adversarial Multi-task Learning for Age Group Classification

Recently, researchers have utilized neural network-based speaker embedding techniques in speaker-recognition tasks to identify speakers accurately. However, speaker-discriminative embeddings do not always represent speech features such as age group well. In an embedding model that has been highly tr...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-01
Main Authors: Baeg, Kwangje, Kim, Yeong-Gwan, Young-Sub Han, Byoung-Ki Jeon
Format: Article
Language:English
Subjects:
Age
Classification
Domains
Embedding
Learning
Neural networks
Speech
Subgroups
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, researchers have utilized neural network-based speaker embedding techniques in speaker-recognition tasks to identify speakers accurately. However, speaker-discriminative embeddings do not always represent speech features such as age group well. In an embedding model that has been highly trained to capture speaker traits, the task of age group classification is closer to speech information leakage. Hence, to improve age group classification performance, we consider the use of speaker-discriminative embeddings derived from adversarial multi-task learning to align features and reduce the domain discrepancy in age subgroups. In addition, we investigated different types of speaker embeddings to learn and generalize the domain-invariant representations for age groups. Experimental results on the VoxCeleb Enrichment dataset verify the effectiveness of our proposed adaptive adversarial network in multi-objective scenarios and leveraging speaker embeddings for the domain adaptation task.
ISSN:2331-8422