paper-with-me

Papers

INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech Recognition

2023-05-25 · Eunseop Yoon, Hee Suk Yoon, John Harvill, Mark Hasegawa-Johnson, Chang D. Yoo

Automatic Speech Recognition (ASR) systems have attained unprecedented performance with large speech models pre-trained based on self-supervised speech representation learning. However, these pre-trained speech models suffer from representational bias as they tend to better represent those prominent accents (i.e., native (L1) English accent) in the pre-training speech corpus than less represented accents, resulting in a deteriorated performance for non-native (L2) English accents. Although there have been some approaches to mitigate this issue, all of these methods require updating the pre-trained model weights. In this paper, we propose Information Theoretic Adversarial Prompt Tuning (INTapt), which introduces prompts concatenated to the original input that can re-modulate the attention of the pre-trained model such that the corresponding input resembles a native (L1) English speech without updating the backbone weights. INTapt is trained simultaneously in the following two manners: (1) adversarial training to reduce accent feature dependence between the original input and the prompt-concatenated input and (2) training to minimize CTC loss for improving ASR performance to a prompt-concatenated input. Experimental results show that INTapt improves the performance of L2 English and increases feature similarity between L2 and L1 accents.

📄 PDF Abstract BibTeX arXiv:2305.16371

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Representation Learningspeech-recognitionSpeech RecognitionSpeech Representation Learning

Methods 이 논문이 사용한 방법론

CTC Loss 설명 없음

Similar Papers 제목 키워드 기반

InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding

2023-06-08 · NeurIPS 2023 11

Soft prompt tuning achieves superior performances across a wide range of few-shot tasks. However, the performances of prompt tuning can be highly sensitive to the initialization of the prompts. We also empirically observ…

Language ModelingLanguage ModellingNatural Language Understanding

FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models

2025-09-03 · Kun Zhai, Siheng Chen, Xingjun Ma, Yu-Gang Jiang arxiv

Federated Prompt Tuning (FPT) is an efficient method for cross-client collaborative fine-tuning of large Vision-Language Models (VLMs). However, models tuned using FPT are vulnerable to adversarial attacks, leading to mi…

Adversarial RobustnessImage Classification

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface

2025-01-16 · Andrey Labunets, Nishit V. Pandya, Ashish Hooda, Xiaohan Fu 외

We surface a new threat to closed-weight Large Language Models (LLMs) that enables an attacker to compute optimization-based prompt injections. Specifically, we characterize how an attacker can leverage the loss-like inf…

Robust Graph Fine-Tuning with Adversarial Graph Prompting

2026-01-01 · Ziyan Zhang, Bo Jiang, Jin Tang arxiv

Parameter-Efficient Fine-Tuning (PEFT) method has emerged as a dominant paradigm for adapting pre-trained GNN models to downstream tasks. However, existing PEFT methods usually exhibit significant vulnerability to variou…

parameter-efficient fine-tuning

The Evaluation Game: Beyond Static LLM Benchmarking

2026-05-19 · Paul Wang, Jade Garcia-Bourrée, Anne-Marie Kermarrec, Vincent Corruble arxiv

As jailbreaks, adversarially crafted inputs that bypass safety constraints, continue to be discovered in Large Language Models, practitioners increasingly rely on fine-tuning as a defensive strategy. Yet the theoretical …

Data Augmentation