Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2111.14203

How Deep Are the Fakes? Focusing on Audio Deepfake: A Survey

Zahra Khanjani·Gabrielle Watson·Vandana P. Janeja
View original source ↗Read source document ↗Export metadata ↓

Abstract

Deepfake is content or material that is synthetically generated or manipulated using artificial intelligence (AI) methods, to be passed off as real and can include audio, video, image, and text synthesis. This survey has been conducted with a different perspective compared to existing survey papers, that mostly focus on just video and image deepfakes. This survey not only evaluates generation and detection methods in the different deepfake categories, but mainly focuses on audio deepfakes that are overlooked in most of the existing surveys. This paper critically analyzes and provides a unique source of audio deepfake research, mostly ranging from 2016 to 2020. To the best of our knowledge, this is the first survey focusing on audio deepfakes in English. This survey provides readers with a summary of 1) different deepfake categories 2) how they could be created and detected 3) the most recent trends in this domain and shortcomings in detection methods 4) audio deepfakes, how they are created and detected in more detail which is the main focus of this paper. We found that Generative Adversarial Networks(GAN), Convolutional Neural Networks (CNN), and Deep Neural Networks (DNN) are common ways of creating and detecting deepfakes. In our evaluation of over 140 methods we found that the majority of the focus is on video deepfakes and in particular in the generation of video deepfakes. We found that for text deepfakes there are more generation methods but very few robust methods for detection, including fake news detection, which has become a controversial area of research because of the potential of heavy overlaps with human generation of fake content. This paper is an abbreviated version of the full survey and reveals a clear need to research audio deepfakes and particularly detection of audio deepfakes.

Explore related subjects

cs.SDcs.AIeess.AS

Keep this discovery

BibTeXRIS

Zahra Khanjani, Gabrielle Watson, Vandana P. Janeja. 2021-11-28. How Deep Are the Fakes? Focusing on Audio Deepfake: A Survey. https://arxiv.org/abs/2111.14203

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗