Exploring WavLM Back-ends for Speech Spoofing and Deepfake Detection

• URL: http://arxiv.org/abs/2409.05032v1
• Date: Sun, 8 Sep 2024 08:54:36 GMT
• Title: Exploring WavLM Back-ends for Speech Spoofing and Deepfake Detection
• Authors: Theophile Stourbe, Victor Miara, Theo Lepage, Reda Dehak,
• Abstract summary: ASVspoof 5 Challenge Track 1: Speech Deepfake Detection - Open Condition consists of a stand-alone speech deepfake (bonafide vs spoof) detection task. We leverage a pre-trained WavLM as a front-end model and pool its representations with different back-end techniques. Our fused system achieves 0.0937 minDCF, 3.42% EER, 0.1927 Cllr, and 0.1375 actDCF.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper describes our submitted systems to the ASVspoof 5 Challenge Track 1: Speech Deepfake Detection - Open Condition, which consists of a stand-alone speech deepfake (bonafide vs spoof) detection task. Recently, large-scale self-supervised models become a standard in Automatic Speech Recognition (ASR) and other speech processing tasks. Thus, we leverage a pre-trained WavLM as a front-end model and pool its representations with different back-end techniques. The complete framework is fine-tuned using only the trained dataset of the challenge, similar to the close condition. Besides, we adopt data-augmentation by adding noise and reverberation using MUSAN noise and RIR datasets. We also experiment with codec augmentations to increase the performance of our method. Ultimately, we use the Bosaris toolkit for score calibration and system fusion to get better Cllr scores. Our fused system achieves 0.0937 minDCF, 3.42% EER, 0.1927 Cllr, and 0.1375 actDCF.

Related papers

• USTC-KXDIGIT System Description for ASVspoof5 Challenge [30.962424920219224]
  This paper describes the USTC-KXDIGIT system submitted to the ASVspoof5 Challenge for Track 1 (speech deepfake detection) and Track 2 (spoofing- automatic speaker verification, SASV) Track 1 showcases a diverse range of technical qualities from potential processing algorithms and includes both open and closed conditions. In Track 2, we continued using the CM system from Track 1 and fused it with a CNN-based ASV system. This approach achieved 0.2814 min-aDCF in the closed condition and 0.0756 min-aDCF in the open condition, showcasing superior performance in
  arXiv  Detail & Related papers  (2024-09-03T08:28:58Z)
• Cross-Domain Audio Deepfake Detection: Dataset and Analysis [11.985093463886056]
  Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a single utterance. We construct a new cross-domain ADD dataset comprising over 300 hours of speech data that is generated by five advanced zero-shot TTS models.
  arXiv  Detail & Related papers  (2024-04-07T10:10:15Z)
• Improved DeepFake Detection Using Whisper Features [2.846767128062884]
  We investigate the influence of Whisper automatic speech recognition model as a DF detection front-end. We show that using Whisper-based features improves the detection for each model and outperforms recent results on the In-The-Wild dataset by reducing Equal Error Rate by 21%.
  arXiv  Detail & Related papers  (2023-06-02T10:34:05Z)
• Jointly Learning Visual and Auditory Speech Representations from Raw Data [108.68531445641769]
  RAVEn is a self-supervised multi-modal approach to jointly learn visual and auditory speech representations. Our design is asymmetric w.r.t. driven by the inherent differences between video and audio. RAVEn surpasses all self-supervised methods on visual speech recognition.
  arXiv  Detail & Related papers  (2022-12-12T21:04:06Z)
• Fully Automated End-to-End Fake Audio Detection [57.78459588263812]
  This paper proposes a fully automated end-toend fake audio detection method. We first use wav2vec pre-trained model to obtain a high-level representation of the speech. For the network structure, we use a modified version of the differentiable architecture search (DARTS) named light-DARTS.
  arXiv  Detail & Related papers  (2022-08-20T06:46:55Z)
• Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models [13.456066434598155]
  We address the problem of detecting speech directed to a device that does not contain a specific wake-word. Specifically, we focus on audio coming from a touch-based invocation.
  arXiv  Detail & Related papers  (2022-03-30T01:27:39Z)
• Spotting adversarial samples for speaker verification by neural vocoders [102.1486475058963]
  We adopt neural vocoders to spot adversarial samples for automatic speaker verification (ASV) We find that the difference between the ASV scores for the original and re-synthesize audio is a good indicator for discrimination between genuine and adversarial samples. Our codes will be made open-source for future works to do comparison.
  arXiv  Detail & Related papers  (2021-07-01T08:58:16Z)
• Continual Learning for Fake Audio Detection [62.54860236190694]
  This paper proposes detecting fake without forgetting, a continual-learning-based method, to make the model learn new spoofing attacks incrementally. Experiments are conducted on the ASVspoof 2019 dataset.
  arXiv  Detail & Related papers  (2021-04-15T07:57:05Z)
• Wake Word Detection with Alignment-Free Lattice-Free MMI [66.12175350462263]
  Always-on spoken language interfaces, e.g. personal digital assistants, rely on a wake word to start processing spoken input. We present novel methods to train a hybrid DNN/HMM wake word detection system from partially labeled training data. We evaluate our methods on two real data sets, showing 50%--90% reduction in false rejection rates at pre-specified false alarm rates over the best previously published figures.
  arXiv  Detail & Related papers  (2020-05-17T19:22:25Z)
• You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation [59.31769998728787]
  We build our TTS system on an ASR training database and then extend the data with synthesized speech to train a recognition model. Our system establishes a competitive result for end-to-end ASR trained on LibriSpeech train-clean-100 set with WER 4.3% for test-clean and 13.5% for test-other.
  arXiv  Detail & Related papers  (2020-05-14T17:24:57Z)

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.