Detecting the Undetectable: Assessing the Efficacy of Current Spoof Detection Methods Against Seamless Speech Edits

• URL: http://arxiv.org/abs/2501.03805v1
• Date: Tue, 07 Jan 2025 14:17:47 GMT
• Title: Detecting the Undetectable: Assessing the Efficacy of Current Spoof Detection Methods Against Seamless Speech Edits
• Authors: Sung-Feng Huang, Heng-Cheng Kuo, Zhehuai Chen, Xuesong Yang, Chao-Han Huck Yang, Yu Tsao, Yu-Chiang Frank Wang, Hung-yi Lee, Szu-Wei Fu,
• Abstract summary: We introduce the Speech INfilling Edit (SINE) dataset, created with Voicebox. Subjective evaluations confirm that speech edited using this novel technique is more challenging to detect than conventional cut-and-paste methods. Despite human difficulty, experimental results demonstrate that self-supervised-based detectors can achieve remarkable performance in detection, localization, and generalization.
• Score: 82.8859060022651
• License:
• Abstract: Neural speech editing advancements have raised concerns about their misuse in spoofing attacks. Traditional partially edited speech corpora primarily focus on cut-and-paste edits, which, while maintaining speaker consistency, often introduce detectable discontinuities. Recent methods, like A\textsuperscript{3}T and Voicebox, improve transitions by leveraging contextual information. To foster spoofing detection research, we introduce the Speech INfilling Edit (SINE) dataset, created with Voicebox. We detailed the process of re-implementing Voicebox training and dataset creation. Subjective evaluations confirm that speech edited using this novel technique is more challenging to detect than conventional cut-and-paste methods. Despite human difficulty, experimental results demonstrate that self-supervised-based detectors can achieve remarkable performance in detection, localization, and generalization across different edit methods. The dataset and related models will be made publicly available.

Related papers

• Phoneme-Level Feature Discrepancies: A Key to Detecting Sophisticated Speech Deepfakes [13.218438914114019]
  Phoneme features provide a powerful speech representation for deepfake detection. We develop a new mechanism for detecting speech deepfakes by identifying the inconsistencies of phoneme-level speech features.
  arXiv  Detail & Related papers  (2024-12-17T07:31:19Z)
• Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models [52.04189118767758]
  Generalization is a main issue for current audio deepfake detectors. In this paper we study the potential of large-scale pre-trained models for audio deepfake detection.
  arXiv  Detail & Related papers  (2024-05-03T15:27:11Z)
• Looking and Listening: Audio Guided Text Recognition [62.98768236858089]
  Text recognition in the wild is a long-standing problem in computer vision. Recent studies suggest vision and language processing are effective for scene text recognition. Yet, solving edit errors such as add, delete, or replace is still the main challenge for existing approaches. We propose the AudioOCR, a simple yet effective probabilistic audio decoder for mel spectrogram sequence prediction.
  arXiv  Detail & Related papers  (2023-06-06T08:08:18Z)
• Adversarial Representation Learning for Robust Privacy Preservation in Audio [11.409577482625053]
  Sound event detection systems may inadvertently reveal sensitive information about users or their surroundings. We propose a novel adversarial training method for learning representations of audio recordings. The proposed method is evaluated against a baseline approach with no privacy measures and a prior adversarial training method.
  arXiv  Detail & Related papers  (2023-04-29T08:39:55Z)
• Deep Learning for Hate Speech Detection: A Comparative Study [54.42226495344908]
  We present here a large-scale empirical comparison of deep and shallow hate-speech detection methods. Our goal is to illuminate progress in the area, and identify strengths and weaknesses in the current state-of-the-art. In doing so we aim to provide guidance as to the use of hate-speech detection in practice, quantify the state-of-the-art, and identify future research directions.
  arXiv  Detail & Related papers  (2022-02-19T03:48:20Z)
• Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information [55.75018546938499]
  We propose the speaker embedding-aware neural diarization (SEND) method, which predicts the power set encoded labels. Our method achieves lower diarization error rate than the target-speaker voice activity detection.
  arXiv  Detail & Related papers  (2021-11-28T12:51:04Z)
• Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration [62.75234183218897]
  We propose a one-stage context-aware framework to generate natural and coherent target speech without any training data of the speaker. We generate the mel-spectrogram of the edited speech with a transformer-based decoder. It outperforms a recent zero-shot TTS engine by a large margin.
  arXiv  Detail & Related papers  (2021-09-12T04:17:53Z)
• Context-Aware Prosody Correction for Text-Based Speech Editing [28.459695630420832]
  A major drawback of current systems is that edited recordings often sound unnatural because of prosody mismatches around edited regions. We propose a new context-aware method for more natural sounding text-based editing of speech.
  arXiv  Detail & Related papers  (2021-02-16T18:16:30Z)

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.