论PSTN、VoIP和神经音频编解码器中的语言与性别偏见
On the Language and Gender Biases in PSTN, VoIP and Neural Audio Codecs
AI总结：
本研究分析超200万多语言音频经PSTN、VoIP及神经编解码器转码后的质量，发现PSTN存在性别偏见，神经编解码器存在语言偏见。
摘要：
近年来，语音技术领域对公平性和包容性的关注日益增加，尤其是在自动语音识别和语音情感分析等领域。当音频在处理前被转码（如在流媒体或实时应用中）时，编码机制中固有的任何偏见都可能导致差异。这不仅影响用户体验，还可能通过延续刻板印象和排斥现象而产生更广泛的社会影响。因此，音频编码机制的无偏见性至关重要。在本工作中，我们为音频编解码器语言和性别偏见方面的稀缺研究做出贡献。通过分析超过200万个多语言音频文件在经过代表性编解码器子集（PSTN、VoIP和神经）转码后的语音质量，我们的结果表明，PSTN编解码器在性别方面存在强烈偏见，而神经编解码器则引入了语言偏见。
英文摘要：
In recent years, there has been a growing focus on fairness and inclusivity within speech technology, particularly in areas such as automatic speech recognition and speech sentiment analysis. When audio is transcoded prior to processing, as is the case in streaming or real-time applications, any inherent bias in the coding mechanism may result in disparities. This not only affects user experience but can also have broader societal implications by perpetuating stereotypes and exclusion. Thus, it is important that audio coding mechanisms are unbiased. In this work, we contribute towards the scarce research with respect to language and gender biases of audio codecs. By analyzing the speech quality of over 2 million multilingual audio files after transcoding through a representative subset of codecs (PSTN, VoIP and neural), our results indicate that PSTN codecs are strongly biased in terms of gender and that neural codecs introduce language biases.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
