automatic speech recognition (ASR) meets more informal and free-form input
data as voice user interfaces and conversational agents such as the voice
assistants such as Alexa, Google Home, etc., gain popularity. Conversational
speech is both the most difficult and environmentally releva
本研究针对自动语音识别的性别、种族、病残等偏见现象,探讨为缓解这些歧视提出的去偏见技术,并讨论设计更具通用性和包容性的语音识别技术。对于每种探讨方法,本文提供研究摘要、应用方法和研究结果,并强调其优点和 / 或缺点。最后,还提出了自然语言处理研究人员应在下一级别的 ASR 技术创新方面探索的未来机会。