The COVID-19 pandemic has led to an increased use of remote telephonic
interviews, making it important to distinguish between scripted and spontaneous
speech in audio recordings. In this paper, we propose a novel scheme for
identifying read and spontaneous speech. Our approach uses a pre-trained
DeepSpeech audio-to-alphabet recognition engine to generate a sequence of
alphabets from the audio. From these alphabets, we derive features that allow
us to discriminate between read and spontaneous speech. Our experimental
results show that even a small set of self-explanatory features can effectively
classify the two types of speech very effectively.

本文提出一种新的方案，通过使用预训练的 DeepSpeech 音频到字母识别引擎加以实现，能够有效地将录音中的自然语音和脚本朗读语音进行识别和分类

一种分类阅读和自发语音的新方案

A Novel Scheme to classify Read and Spontaneous Speech

We construct audio adversarial examples on automatic Speech-To-Text systems .
Given any audio waveform, we produce an another by overlaying an audio vocal
mask generated from the original audio. We apply our audio adversarial attack
to five SOTA STT systems: DeepSpeech, Julius, Kaldi, wav2letter@anywhere and
CMUSphinx. In addition, we engaged human annotators to transcribe the
adversarial audio. Our experiments show that these adversarial examples fool
State-Of-The-Art Speech-To-Text systems, yet humans are able to consistently
pick out the speech. The feasibility of this attack introduces a new domain to
study machine and human perception of speech.

我们构造了针对自动语音转文字系统的音频对抗样本，并将其应用于五种最先进的语音转文字系统，实验证明这些对抗样本可以欺骗机器，但人类可以轻易地辨识出其中的话语。这一攻击的可行性为研究机器和人类对话语的感知提供了一个新的领域。

音频对抗样本：利用语音面具的攻击

Audio Adversarial Examples: Attacks Using Vocal Masks

We construct targeted audio adversarial examples on automatic speech
recognition. Given any audio waveform, we can produce another that is over
99.9% similar, but transcribes as any phrase we choose (recognizing up to 50
characters per second of audio). We apply our white-box iterative
optimization-based attack to Mozilla's implementation DeepSpeech end-to-end,
and show it has a 100% success rate. The feasibility of this attack introduce a
new domain to study adversarial examples.

利用白盒迭代优化算法针对 Mozilla 的 DeepSpeech 实现针对性的音频对抗性样本进行攻击，成功率为 100％，这种攻击的可行性引入了研究对抗性样本的新领域。