GE2E-AC: Generalized End-to-End Loss Training for Accent Classification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Watanabe, Chihiro, Kameoka, Hirokazu
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910626226372608
author Watanabe, Chihiro
Kameoka, Hirokazu
author_facet Watanabe, Chihiro
Kameoka, Hirokazu
contents Accent classification or AC is a task to predict the accent type of an input utterance, and it can be used as a preliminary step toward accented speech recognition and accent conversion. Existing studies have often achieved such classification by training a neural network model to minimize the classification error of the predicted accent label, which can be obtained as a model output. Since we optimize the entire model only from the perspective of classification loss during training time in this approach, the model might learn to predict the accent type from irrelevant features, such as individual speaker identity, which are not informative during test time. To address this problem, we propose a GE2E-AC, in which we train a model to extract accent embedding or AE of an input utterance such that the AEs of the same accent class get closer, instead of directly minimizing the classification loss. We experimentally show the effectiveness of the proposed GE2E-AC, compared to the baseline model trained with the conventional cross-entropy-based loss.
format Preprint
id arxiv_https___arxiv_org_abs_2407_14021
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GE2E-AC: Generalized End-to-End Loss Training for Accent Classification
Watanabe, Chihiro
Kameoka, Hirokazu
Audio and Speech Processing
Sound
Machine Learning
Accent classification or AC is a task to predict the accent type of an input utterance, and it can be used as a preliminary step toward accented speech recognition and accent conversion. Existing studies have often achieved such classification by training a neural network model to minimize the classification error of the predicted accent label, which can be obtained as a model output. Since we optimize the entire model only from the perspective of classification loss during training time in this approach, the model might learn to predict the accent type from irrelevant features, such as individual speaker identity, which are not informative during test time. To address this problem, we propose a GE2E-AC, in which we train a model to extract accent embedding or AE of an input utterance such that the AEs of the same accent class get closer, instead of directly minimizing the classification loss. We experimentally show the effectiveness of the proposed GE2E-AC, compared to the baseline model trained with the conventional cross-entropy-based loss.
title GE2E-AC: Generalized End-to-End Loss Training for Accent Classification
topic Audio and Speech Processing
Sound
Machine Learning
url https://arxiv.org/abs/2407.14021