Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

audio-2

Synthetic Speech Detection

3260 papers • 126 benchmarks • 313 datasets

Detect fake synthetic speech generated using machine learning

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in synthetic-speech-detection-8

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find synthetic-speech-detection-8 models and implementations

Datasets

DEEP-VOICE: DeepFake Voice Recognition

Synthetic Speech Attribution

Subtasks

No subtasks available.

Most implemented papers

Replay and Synthetic Speech Detection with Res2Net Architecture

Chao Weng, N. Li, Xu Li, Xunying Liu, Dan Su, Dong Yu, H. Meng•Tue Oct 27 2020

The Res2Net model consistently outperforms ResNet34 and ResNet50 by a large margin in both physical access (PA) and logical access (LA) of the ASVspoof 2019 corpus and the constant-Q transform (CQT) achieves the most promising performance in both PA and LA scenarios.

192

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021

Z. Duan, Ge Zhu, You Zhang, Xinhui Chen•Sun Jul 25 2021

UR-AIR system submission to the logical access (LA) and the speech deepfake (DF) tracks of the ASVspoof 2021 Challenge is presented and a channel-robust synthetic speech detection system for the challenge is proposed.

60 0

Paper Graph

ConvNeXt Based Neural Network for Audio Anti-Spoofing

Qiaowei Ma, J. Zhong, Weiheng Liu, Yingbo Gao, W. W. Ng•Tue Sep 13 2022

Inspired by the promising performance of ConvNeXt in image classification tasks, the ConvNext network architecture is revised and a lightweight end-to-end anti-spoofing model is proposed that can focus on the most informative sub-bands of speech representations and the difficult samples that are hard to classify.

5 0

Paper Graph

FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection

Xianfeng Zhao, Zhenyu Zhang, Yewei Gu, Xiaowei Yi•Sun Oct 17 2021

A challenging Mandarin dataset is constructed and the accompanying audio track of the first fake media forensic challenge of China Society of Image and Graphics (FMFCC-A) is organized, to fill the gap of lack of Mandarin datasets for synthetic speech detection.

35 0

Paper Graph

Towards End-to-End Synthetic Speech Detection

Haijian Zhang, Guang Hua, A. Teoh•Thu Jun 10 2021

It is shown that by only using standard components, a light-weight neural network could outperform the state-of-the-art methods for the ASVspoof2019 challenge, and the proposed model is termed Time-domain Synthetic Speech Detection Net (TSSDNet), having ResNet- or Inception-style structures.

175 0

Paper Graph

The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection

S. Milani, Daniele Mari, Federica Latora•Wed Oct 05 2022

This work investigates the discriminative role of silenced parts in synthetic speech detection and shows how first digit statistics extracted from MFCC coefficients can efficiently enable a robust detection.

12 0

Paper Graph

SingFake: Singing Voice Deepfake Detection

Yongyi Zang, You Zhang, Mojtaba Heydari, Zhiyao Duan•Wed Sep 13 2023

The SingFake dataset is presented, the first curated in-the-wild dataset consisting of 28.93 hours of bonafide and 29.40 hours of deepfake song clips in five languages from 40 singers, and four state-of-the-art speech countermeasure systems trained on speech utterances are evaluated.

53 0

Paper Graph

Adding a benchmark result helps the community track progress.

Synthetic Speech Detection | State-of-the-Art