XLSR-Kanformer: A KAN-Intergrated model for Synthetic Speech Detection

• URL: http://arxiv.org/abs/2510.06706v1
• Date: Wed, 08 Oct 2025 06:58:58 GMT
• Title: XLSR-Kanformer: A KAN-Intergrated model for Synthetic Speech Detection
• Abstract summary: We propose a novel approach that replaces the traditional Multi-Layer Perceptron (MLP) in the XLSR-Conformer model with a Kolmogorov-Arnold Network (KAN)<n>Our experimental results demonstrate that the integration of KAN to XLSR-Conformer model can improve the performance by 60.55% relatively in Equal Error Rate (EER) LA and DF sets.
• Score: 1.8334165690218873
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in speech synthesis technologies have led to increasingly sophisticated spoofing attacks, posing significant challenges for automatic speaker verification systems. While systems based on self-supervised learning (SSL) models, particularly the XLSR-Conformer architecture, have demonstrated remarkable performance in synthetic speech detection, there remains room for architectural improvements. In this paper, we propose a novel approach that replaces the traditional Multi-Layer Perceptron (MLP) in the XLSR-Conformer model with a Kolmogorov-Arnold Network (KAN), a powerful universal approximator based on the Kolmogorov-Arnold representation theorem. Our experimental results on ASVspoof2021 demonstrate that the integration of KAN to XLSR-Conformer model can improve the performance by 60.55% relatively in Equal Error Rate (EER) LA and DF sets, further achieving 0.70% EER on the 21LA set. Besides, the proposed replacement is also robust to various SSL architectures. These findings suggest that incorporating KAN into SSL-based models is a promising direction for advances in synthetic speech detection.

Related papers

• Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack [7.2972297703292135]
  KEYAC is a dataset designed to analyze representation generalization for ASCA under both standard and VoIP settings.<n>We evaluate six representation learning models under zero-shot and partial fine-tuning settings using fully connected and convolutional networks.<n>Results show that while partial fine-tuning improves performance, models struggle to generalize across VoIP codecs.
  arXiv  Detail & Related papers  (2026-06-19T08:26:11Z)
• Consistency-Regularized GAN for Few-Shot SAR Target Recognition [40.2533418376231]
  Few-shot recognition in synthetic aperture radar (SAR) imagery remains a critical bottleneck for real-world applications due to extreme data scarcity.<n>A promising strategy involves a large dataset with a generative adversarial network (GAN), pre-training a model via self-supervised learning (SSL), and then fine-tuning on the few labeled samples.<n>This approach faces a fundamental paradox: conventional GANs themselves require abundant data for stable training, contradicting the premise of few-shot learning.<n>We propose the consistency-regularized generative adversarial network (Cr-GAN), a novel framework designed to synthesize diverse, high
  arXiv  Detail & Related papers  (2026-01-22T06:02:39Z)
• From Memorization to Creativity: LLM as a Designer of Novel Neural-Architectures [48.83701310501069]
  Large language models (LLMs) excel in program synthesis, yet their ability to autonomously navigate neural architecture design-balancing reliability, performance, and structural novelty--remains underexplored.<n>We address this by placing a code-oriented LLM within a closed-loop synthesis framework, analyzing its evolution over 22 supervised fine-tuning cycles.
  arXiv  Detail & Related papers  (2026-01-06T13:20:28Z)
• Large-Scale Model Enabled Semantic Communication Based on Robust Knowledge Distillation [45.347078403677216]
  Large-scale models (LSMs) can be an effective framework for semantic representation and understanding.<n>However, their direct deployment is often hindered by high computational complexity and resource requirements.<n>This paper proposes a novel knowledge distillation based semantic communication framework.
  arXiv  Detail & Related papers  (2025-08-04T07:47:18Z)
• Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models [1.7205106391379026]
  We propose a novel approach that replaces the traditional Multi-Layer Perceptron in the XLSR-Conformer model with a Kolmogorov-Arnold Network (KAN)<n>Our results show that integrating KAN into the SSL-based models can improve the performance by 60.55% relatively on LA and DF sets.
  arXiv  Detail & Related papers  (2025-06-17T03:30:58Z)
• Revisiting SSL for sound event detection: complementary fusion and adaptive post-processing [13.761237056969]
  Self-supervised learning (SSL) models offer powerful representations for sound event detection (SED)<n>This study systematically evaluates state-of-the-art SSL models to guide optimal model selection and integration for SED.<n>We propose a framework that combines heterogeneous SSL representations through three fusion strategies: individual SSL embedding integration, dual-modal fusion, and full aggregation.
  arXiv  Detail & Related papers  (2025-05-17T07:54:31Z)
• Improving Transducer-Based Spoken Language Understanding with Self-Conditioned CTC and Knowledge Transfer [11.362681035467121]
  We propose to improve end-to-end (E2E) spoken language understand (SLU) in an RNN transducer model (RNN-T)<n>Our proposed model is akin to an E2E differentiable cascaded model which performs ASR and SLU sequentially.
  arXiv  Detail & Related papers  (2025-01-03T18:19:12Z)
• Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition [71.87998918300806]
  This paper explores approaches to integrate domain fine-tuned SSL pre-trained models and their features into TDNN and Conformer ASR systems. TDNN systems constructed by integrating domain-adapted HuBERT, wav2vec2-conformer or multi-lingual XLSR models consistently outperform standalone fine-tuned SSL pre-trained models. Consistent improvements in Alzheimer's Disease detection accuracy are also obtained using the DementiaBank Pitt elderly speech recognition outputs.
  arXiv  Detail & Related papers  (2024-07-03T08:33:39Z)
• Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Filling [13.515248068374625]
  We propose to use an encoder pretrained on speech recognition (ASR) to initialize an end-to-end (E2E) Conformer-Transformer model. Our model achieves the new state-of-the-art results on the SLURP dataset, with 90.14% intent accuracy and 82.27% SLURP-F1.
  arXiv  Detail & Related papers  (2023-07-13T20:50:19Z)
• Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices [59.86658316440461]
  We present a robust and low complexity system for Acoustic Scene Classification (ASC) We first construct an ASC baseline system in which a novel inception-residual-based network architecture is proposed to deal with the mismatched recording device issue. To further improve the performance but still satisfy the low complexity model, we apply two techniques: ensemble of multiple spectrograms and channel reduction.
  arXiv  Detail & Related papers  (2022-03-23T10:27:41Z)
• Conformer-based Hybrid ASR System for Switchboard Dataset [99.88988282353206]
  We present and evaluate a competitive conformer-based hybrid model training recipe. We study different training aspects and methods to improve word-error-rate as well as to increase training speed. We conduct experiments on Switchboard 300h dataset and our conformer-based hybrid model achieves competitive results.
  arXiv  Detail & Related papers  (2021-11-05T12:03:18Z)
• 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)
• A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification [78.04177357888284]
  We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC) We report an efficient joint framework for low-complexity multi-device ASC, called Acoustic Lottery.
  arXiv  Detail & Related papers  (2021-07-03T16:25:24Z)
• Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit [41.85906379846473]
  We show that DGP can be applied to utterance-level modeling using recurrent architecture models. We adopt a simple recurrent unit (SRU) for the proposed model to achieve a recurrent architecture. The proposed SRU-DGP-based speech synthesis outperforms not only feed-forward DGP but also automatically tuned SRU- and long short-term memory (LSTM)-based neural networks.
  arXiv  Detail & Related papers  (2020-04-22T19:51:36Z)

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.