Beyond Neural-on-Neural Approaches to Speaker Gender Protection

• URL: http://arxiv.org/abs/2306.17700v1
• Date: Fri, 30 Jun 2023 14:26:49 GMT
• Title: Beyond Neural-on-Neural Approaches to Speaker Gender Protection
• Authors: Loes van Bemmel, Zhuoran Liu, Nik Vaessen, Martha Larson
• Abstract summary: We show the importance of testing gender inference attacks based on speech features. We argue that researchers should use speech features to gain insight into how protective modifications change the speech signal.
• Score: 2.741893145546753
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent research has proposed approaches that modify speech to defend against gender inference attacks. The goal of these protection algorithms is to control the availability of information about a speaker's gender, a privacy-sensitive attribute. Currently, the common practice for developing and testing gender protection algorithms is "neural-on-neural", i.e., perturbations are generated and tested with a neural network. In this paper, we propose to go beyond this practice to strengthen the study of gender protection. First, we demonstrate the importance of testing gender inference attacks that are based on speech features historically developed by speech scientists, alongside the conventionally used neural classifiers. Next, we argue that researchers should use speech features to gain insight into how protective modifications change the speech signal. Finally, we point out that gender-protection algorithms should be compared with novel "vocal adversaries", human-executed voice adaptations, in order to improve interpretability and enable before-the-mic protection.

Related papers

• Machine Unlearning reveals that the Gender-based Violence Victim Condition can be detected from Speech in a Speaker-Agnostic Setting [0.0]
  This study addresses the critical issue of gender-based violence's (GBV) impact on women's mental health. GBV often results in long-lasting adverse effects for the victims, including anxiety, depression, post-traumatic stress disorder (PTSD) Our research presents a novel approach to speaker-agnostic detection of the gender-based violence victim condition (GBVVC)
  arXiv  Detail & Related papers  (2024-11-27T09:53:53Z)
• Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition [56.69875958980474]
  This work considers approaches to defending learned systems and how security defenses result in performance inequities across different sub-populations. We find that many methods that have been proposed can cause direct harm, like false rejection and unequal benefits from robustness training. We present a comparison of equality between two rejection-based defenses: randomized smoothing and neural rejection, finding randomized smoothing more equitable due to the sampling mechanism for minority groups.
  arXiv  Detail & Related papers  (2023-02-17T16:19:26Z)
• Overlapped speech and gender detection with WavLM pre-trained features [6.054285771277486]
  This article focuses on overlapped speech and gender detection in order to study interactions between women and men in French audiovisual media. We propose to use WavLM model which has the advantage of being pre-trained on a huge amount of speech data. A neural GD is trained with WavLM inputs on a gender balanced subset of the French broadcast news ALLIES data, and obtains an accuracy of 97.9%.
  arXiv  Detail & Related papers  (2022-09-09T08:00:47Z)
• Generating gender-ambiguous voices for privacy-preserving speech recognition [38.733077459065704]
  We present a generative adversarial network, GenGAN, that synthesises voices that conceal the gender or identity of a speaker. We condition the generator only on gender information and use an adversarial loss between signal distortion and privacy preservation.
  arXiv  Detail & Related papers  (2022-07-03T14:23:02Z)
• Toward a realistic model of speech processing in the brain with self-supervised learning [67.7130239674153]
  Self-supervised algorithms trained on the raw waveform constitute a promising candidate. We show that Wav2Vec 2.0 learns brain-like representations with as little as 600 hours of unlabelled speech.
  arXiv  Detail & Related papers  (2022-06-03T17:01:46Z)
• Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition [12.024098046435796]
  Speech data cannot be protected when uploaded and processed on servers in internet-of-things applications. Deep neural networks have proven to be vulnerable to human-indistinguishable adversarial perturbations. We propose a novel federated adversarial learning framework for protecting both data and deep neural networks.
  arXiv  Detail & Related papers  (2022-03-09T13:19:26Z)
• Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution [83.84968082791444]
  Deep neural networks are vulnerable to intentionally crafted adversarial examples. Various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models.
  arXiv  Detail & Related papers  (2021-08-29T08:11:36Z)
• Protecting gender and identity with disentangled speech representations [49.00162808063399]
  We show that protecting gender information in speech is more effective than modelling speaker-identity information. We present a novel way to encode gender information and disentangle two sensitive biometric identifiers.
  arXiv  Detail & Related papers  (2021-04-22T13:31:41Z)
• A Review of Speaker Diarization: Recent Advances with Deep Learning [78.20151731627958]
  Speaker diarization is a task to label audio or video recordings with classes corresponding to speaker identity. With the rise of deep learning technology, more rapid advancements have been made for speaker diarization. We discuss how speaker diarization systems have been integrated with speech recognition applications.
  arXiv  Detail & Related papers  (2021-01-24T01:28:05Z)
• Gender Stereotype Reinforcement: Measuring the Gender Bias Conveyed by Ranking Algorithms [68.85295025020942]
  We propose the Gender Stereotype Reinforcement (GSR) measure, which quantifies the tendency of a Search Engines to support gender stereotypes. GSR is the first specifically tailored measure for Information Retrieval, capable of quantifying representational harms.
  arXiv  Detail & Related papers  (2020-09-02T20:45:04Z)

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.