Dialect Identification Using Resource-Efficient Fine-Tuning Approaches

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lin, Zirui, Gulzar, Haris, Busto, Monnika Roslianna, Masaki, Akiko, Eda, Takeharu, Nakadai, Kazuhiro
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917117625892864
author Lin, Zirui
Gulzar, Haris
Busto, Monnika Roslianna
Masaki, Akiko
Eda, Takeharu
Nakadai, Kazuhiro
author_facet Lin, Zirui
Gulzar, Haris
Busto, Monnika Roslianna
Masaki, Akiko
Eda, Takeharu
Nakadai, Kazuhiro
contents Dialect Identification (DI) is a task to recognize different dialects within the same language from a speech signal. DI can help to improve the downstream speech related tasks even when speakers have a strong dialect. However, fine-tuning a speech model for tasks like DI is expensive in terms of computation cost and memory requirement. Recent studies have explored fine-tuning pre-trained speech models for tasks like DI using Parameter-Efficient Fine-Tuning (PEFT) methods, which offer parameter efficiency but limited improvement in memory efficiency and training speed. To address these challenges, we explore Memory-Efficient Fine-Tuning (MEFT) methods, originally proposed for language processing, and apply them to the general-purpose pre-trained speech model. We then comprehensively analyze the GPU memory usage and fine-tuning speed based on various MEFT methods. As a case study, we fine-tune the Whisper model to identify six Mandarin subdialects from the KeSpeech dataset, reducing GPU memory usage by up to 73.25% and accelerating training speed by a factor of 2.1, while maintaining accuracy comparable to vanilla fine-tuning and PEFT methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02074
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dialect Identification Using Resource-Efficient Fine-Tuning Approaches
Lin, Zirui
Gulzar, Haris
Busto, Monnika Roslianna
Masaki, Akiko
Eda, Takeharu
Nakadai, Kazuhiro
Computation and Language
Sound
Dialect Identification (DI) is a task to recognize different dialects within the same language from a speech signal. DI can help to improve the downstream speech related tasks even when speakers have a strong dialect. However, fine-tuning a speech model for tasks like DI is expensive in terms of computation cost and memory requirement. Recent studies have explored fine-tuning pre-trained speech models for tasks like DI using Parameter-Efficient Fine-Tuning (PEFT) methods, which offer parameter efficiency but limited improvement in memory efficiency and training speed. To address these challenges, we explore Memory-Efficient Fine-Tuning (MEFT) methods, originally proposed for language processing, and apply them to the general-purpose pre-trained speech model. We then comprehensively analyze the GPU memory usage and fine-tuning speed based on various MEFT methods. As a case study, we fine-tune the Whisper model to identify six Mandarin subdialects from the KeSpeech dataset, reducing GPU memory usage by up to 73.25% and accelerating training speed by a factor of 2.1, while maintaining accuracy comparable to vanilla fine-tuning and PEFT methods.
title Dialect Identification Using Resource-Efficient Fine-Tuning Approaches
topic Computation and Language
Sound
url https://arxiv.org/abs/2512.02074