Language Dependencies in Adversarial Attacks on Speech Recognition
Systems
- URL: http://arxiv.org/abs/2202.00399v2
- Date: Wed, 2 Feb 2022 13:10:07 GMT
- Title: Language Dependencies in Adversarial Attacks on Speech Recognition
Systems
- Authors: Karla Markert and Donika Mirdita and Konstantin B\"ottinger
- Abstract summary: We compare the attackability of a German and an English ASR system.
We investigate if one of the language models is more susceptible to manipulations than the other.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Automatic speech recognition (ASR) systems are ubiquitously present in our
daily devices. They are vulnerable to adversarial attacks, where manipulated
input samples fool the ASR system's recognition. While adversarial examples for
various English ASR systems have already been analyzed, there exists no
inter-language comparative vulnerability analysis. We compare the attackability
of a German and an English ASR system, taking Deepspeech as an example. We
investigate if one of the language models is more susceptible to manipulations
than the other. The results of our experiments suggest statistically
significant differences between English and German in terms of computational
effort necessary for the successful generation of adversarial examples. This
result encourages further research in language-dependent characteristics in the
robustness analysis of ASR.
Related papers
- Reexamining Racial Disparities in Automatic Speech Recognition Performance: The Role of Confounding by Provenance [7.882996636086014]
It is important that automatic speech recognition (ASR) models and their use is fair and equitable.
The current study seeks to understand the factors underlying this disparity by examining the performance of the current state-of-the-art neural network based ASR system.
arXiv Detail & Related papers (2024-07-19T02:14:17Z) - Towards Unsupervised Speech Recognition Without Pronunciation Models [57.222729245842054]
Most languages lack sufficient paired speech and text data to effectively train automatic speech recognition systems.
We propose the removal of reliance on a phoneme lexicon to develop unsupervised ASR systems.
We experimentally demonstrate that an unsupervised speech recognizer can emerge from joint speech-to-speech and text-to-text masked token-infilling.
arXiv Detail & Related papers (2024-06-12T16:30:58Z) - The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese [5.308321515594125]
This study is dedicated to a comprehensive exploration of the Whisper and MMS systems.
Our investigation encompasses various categories, including gender, age, skin tone color, and geo-location.
We empirically show that oversampling techniques alleviate such stereotypical biases.
arXiv Detail & Related papers (2024-02-12T09:35:13Z) - Lost In Translation: Generating Adversarial Examples Robust to
Round-Trip Translation [66.33340583035374]
We present a comprehensive study on the robustness of current text adversarial attacks to round-trip translation.
We demonstrate that 6 state-of-the-art text-based adversarial attacks do not maintain their efficacy after round-trip translation.
We introduce an intervention-based solution to this problem, by integrating Machine Translation into the process of adversarial example generation.
arXiv Detail & Related papers (2023-07-24T04:29:43Z) - Investigating the Sensitivity of Automatic Speech Recognition Systems to
Phonetic Variation in L2 Englishes [3.198144010381572]
This work demonstrates a method of probing an ASR system to discover how it handles phonetic variation across a number of L2 Englishes.
It is demonstrated that the behaviour of the ASR is systematic and consistent across speakers with similar spoken varieties.
arXiv Detail & Related papers (2023-05-12T11:29:13Z) - Robustifying automatic speech recognition by extracting slowly varying
features [20.96846497286073]
We propose a defense mechanism against targeted adversarial attacks.
We use hybrid ASR models trained on data pre-processed in such a way.
Our model shows a performance on clean data similar to the baseline model, while being more than four times more robust.
arXiv Detail & Related papers (2021-12-14T13:50:23Z) - Sequence-level self-learning with multiple hypotheses [53.04725240411895]
We develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR)
In contrast to conventional unsupervised learning approaches, we adopt the emphmulti-task learning (MTL) framework.
Our experiment results show that our method can reduce the WER on the British speech data from 14.55% to 10.36% compared to the baseline model trained with the US English data only.
arXiv Detail & Related papers (2021-12-10T20:47:58Z) - Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of
Language Models [86.02610674750345]
Adversarial GLUE (AdvGLUE) is a new multi-task benchmark to explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks.
We apply 14 adversarial attack methods to GLUE tasks to construct AdvGLUE, which is further validated by humans for reliable annotations.
All the language models and robust training methods we tested perform poorly on AdvGLUE, with scores lagging far behind the benign accuracy.
arXiv Detail & Related papers (2021-11-04T12:59:55Z) - AES Systems Are Both Overstable And Oversensitive: Explaining Why And
Proposing Defenses [66.49753193098356]
We investigate the reason behind the surprising adversarial brittleness of scoring models.
Our results indicate that autoscoring models, despite getting trained as "end-to-end" models, behave like bag-of-words models.
We propose detection-based protection models that can detect oversensitivity and overstability causing samples with high accuracies.
arXiv Detail & Related papers (2021-09-24T03:49:38Z) - LeBenchmark: A Reproducible Framework for Assessing Self-Supervised
Representation Learning from Speech [63.84741259993937]
Self-Supervised Learning (SSL) using huge unlabeled data has been successfully explored for image and natural language processing.
Recent works also investigated SSL from speech.
We propose LeBenchmark: a reproducible framework for assessing SSL from speech.
arXiv Detail & Related papers (2021-04-23T08:27:09Z) - Quantifying Bias in Automatic Speech Recognition [28.301997555189462]
This paper quantifies the bias of a Dutch SotA ASR system against gender, age, regional accents and non-native accents.
Based on our findings, we suggest bias mitigation strategies for ASR development.
arXiv Detail & Related papers (2021-03-28T12:52:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.