mlsanityData to 7 Oct 2026

Dialect Identification Using Resource-Efficient Fine-Tuning Approaches

arXiv 2512.02074 ↗First posted 30 Nov 2025cs.CL cs.SDcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 30 Nov 2025.

Builds on

23 of 37 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  4. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  6. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  7. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
  8. 2017Mixed Precision Trainingcited by 1,135
  9. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 780
  10. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  11. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  12. 20218-bit Optimizers via Block-wise Quantizationcited by 395
11 more
  1. 2023Fine-Tuning Language Models with Just Forward Passescited by 337
  2. 2022LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learningcited by 228
  3. 2021Self-attention Does Not Need O(n2) Memorycited by 152
  4. 2021Fine-tuning wav2vec2 for speaker recognitioncited by 35
  5. 2022Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognitioncited by 31
  6. 2023Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuningcited by 29
  7. 2023UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memorycited by 26
  8. 2024SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learningcited by 11
  9. 2023Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognitioncited by 10
  10. 2023A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Modelcited by 8
  11. 2023Improving Speech Recognition for African American English With Audio Classificationcited by 4

Built on by

Not cited yet.