Voice anonymization techniques have been found to successfully obscure a speaker's acoustic identity in short, isolated utterances in benchmarks such as the VoicePrivacy Challenge. In practice, however, utterances seldom occur in isolation: long-form audio is commonplace in domains such as interviews, phone calls, and meetings. In these cases, many utterances from the same speaker are available, which pose a significantly greater privacy risk: given multiple utterances from the same speaker, an attacker could exploit an individual's vocabulary, syntax, and turns of phrase to re-identify them, even when their voice is completely disguised. To address this risk, we propose a new approach that performs a contextual rewriting of the transcripts in an ASR-TTS pipeline to eliminate speaker-specific style while preserving meaning. We present results in a long-form telephone conversation setting demonstrating the effectiveness of a content-based attack on voice-anonymized speech. Then we show how the proposed content-based anonymization methods can mitigate this risk while preserving speech utility. Overall, we find that paraphrasing is an effective defense against content-based attacks and recommend that stakeholders adopt this step to ensure anonymity in long-form audio.

翻译：语音匿名化技术已被证实能在诸如VoicePrivacy挑战赛等基准测试中，成功掩盖说话者在简短孤立话语中的声学身份。然而在实际应用中，话语很少孤立出现：在访谈、电话通话和会议等领域，长时音频十分普遍。这种情况下，同一说话者的多段话语会构成显著更高的隐私风险：攻击者利用个体特有的词汇、句法和表达方式，即使在其声音被完全伪装的情况下，仍可能通过同一说话者的多段话语实现再识别。为应对此风险，我们提出一种新方法，通过在ASR-TTS流程中对文本转录进行上下文重写，在保持语义的同时消除说话者特定风格。我们在长时电话对话场景中展示了基于内容的攻击对语音匿名化处理的有效性，进而证明所提出的基于内容的匿名化方法如何在保持语音实用性的同时降低此类风险。总体而言，我们发现文本复述是对抗基于内容攻击的有效防御手段，建议相关方采用此步骤以确保长时音频的匿名性。