Improving Generalization for AI-Synthesized Voice Detection

• URL: http://arxiv.org/abs/2412.19279v2
• Date: Mon, 30 Dec 2024 16:08:39 GMT
• Title: Improving Generalization for AI-Synthesized Voice Detection
• Authors: Hainan Ren, Li Lin, Chun-Hao Liu, Xin Wang, Shu Hu,
• Abstract summary: We introduce an innovative disentanglement framework aimed at extracting domain-agnostic artifact features related to vocoders. We enhance model learning in a flat loss landscape, enabling escape from suboptimal solutions and improving generalization.
• Score: 13.5672344219478
• License:
• Abstract: AI-synthesized voice technology has the potential to create realistic human voices for beneficial applications, but it can also be misused for malicious purposes. While existing AI-synthesized voice detection models excel in intra-domain evaluation, they face challenges in generalizing across different domains, potentially becoming obsolete as new voice generators emerge. Current solutions use diverse data and advanced machine learning techniques (e.g., domain-invariant representation, self-supervised learning), but are limited by predefined vocoders and sensitivity to factors like background noise and speaker identity. In this work, we introduce an innovative disentanglement framework aimed at extracting domain-agnostic artifact features related to vocoders. Utilizing these features, we enhance model learning in a flat loss landscape, enabling escape from suboptimal solutions and improving generalization. Extensive experiments on benchmarks show our approach outperforms state-of-the-art methods, achieving up to 5.12% improvement in the equal error rate metric in intra-domain and 7.59% in cross-domain evaluations.

Related papers

• Acoustic Model Optimization over Multiple Data Sources: Merging and Valuation [13.009945735929445]
  We propose a novel paradigm to solve salient problems plaguing the Automatic Speech Recognition field. In the first stage, multiple acoustic models are trained based upon different subsets of the complete speech data. In the second stage, two novel algorithms are utilized to generate a high-quality acoustic model.
  arXiv  Detail & Related papers  (2024-10-21T03:48:23Z)
• SONAR: A Synthetic AI-Audio Detection Framework and Benchmark [59.09338266364506]
  SONAR is a synthetic AI-Audio Detection Framework and Benchmark. It aims to provide a comprehensive evaluation for distinguishing cutting-edge AI-synthesized auditory content. It is the first framework to uniformly benchmark AI-audio detection across both traditional and foundation model-based deepfake detection systems.
  arXiv  Detail & Related papers  (2024-10-06T01:03:42Z)
• Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models [84.8919069953397]
  Self-TAught Recognizer (STAR) is an unsupervised adaptation framework for speech recognition systems. We show that STAR achieves an average of 13.5% relative reduction in word error rate across 14 target domains. STAR exhibits high data efficiency that only requires less than one-hour unlabeled data.
  arXiv  Detail & Related papers  (2024-05-23T04:27:11Z)
• Benchmarking Cross-Domain Audio-Visual Deception Detection [45.342156006617394]
  We present the first cross-domain audio-visual deception detection benchmark. We compare single-to-single and multi-to-single domain generalization performance. We propose an algorithm to enhance the generalization performance.
  arXiv  Detail & Related papers  (2024-05-11T12:06:31Z)
• From Denoising Training to Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation [8.36463803956324]
  We propose the Denoising Y-Net (DeY-Net), a novel approach incorporating an auxiliary denoising decoder into the basic U-Net architecture. The auxiliary decoder aims to perform denoising training, augmenting the domain-invariant representation that facilitates domain generalization. Building upon denoising training, we propose Denoising Test Time Adaptation (DeTTA) that further: (i) adapts the model to the target domain in a sample-wise manner, and (ii) adapts to the noise-corrupted input.
  arXiv  Detail & Related papers  (2023-10-31T08:39:15Z)
• DASA: Difficulty-Aware Semantic Augmentation for Speaker Verification [55.306583814017046]
  We present a novel difficulty-aware semantic augmentation (DASA) approach for speaker verification. DASA generates diversified training samples in speaker embedding space with negligible extra computing cost. The best result achieves a 14.6% relative reduction in EER metric on CN-Celeb evaluation set.
  arXiv  Detail & Related papers  (2023-10-18T17:07:05Z)
• Self-attention fusion for audiovisual emotion recognition with incomplete data [103.70855797025689]
  We consider the problem of multimodal data analysis with a use case of audiovisual emotion recognition. We propose an architecture capable of learning from raw data and describe three variants of it with distinct modality fusion mechanisms.
  arXiv  Detail & Related papers  (2022-01-26T18:04:29Z)
• Factorized Neural Transducer for Efficient Language Model Adaptation [51.81097243306204]
  We propose a novel model, factorized neural Transducer, by factorizing the blank and vocabulary prediction. It is expected that this factorization can transfer the improvement of the standalone language model to the Transducer for speech recognition. We demonstrate that the proposed factorized neural Transducer yields 15% to 20% WER improvements when out-of-domain text data is used for language model adaptation.
  arXiv  Detail & Related papers  (2021-09-27T15:04:00Z)
• Toward Cross-Domain Speech Recognition with End-to-End Models [18.637636841477]
  In this paper, we empirically examine the difference in behavior between hybrid acoustic models and neural end-to-end systems. We show that for the hybrid models, supplying additional training data from other domains with mismatched acoustic conditions does not increase the performance on specific domains. Our end-to-end models optimized with sequence-based criterion generalize better than the hybrid models on diverse domains.
  arXiv  Detail & Related papers  (2020-03-09T15:19:53Z)

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.