Simplified Audio Production in Asynchronous Voice-Based Discussions.
CHI(2016)
摘要
Voice communication adds nuance and expressivity to virtual discussions, but its one-shot nature tends to discourage collaborators from utilizing it. However, text-based interfaces have made voice editing much easier, especially with recent advancements enabling live, time-aligned speech transcription. We introduce SimpleSpeech, an easy-to-use platform for asynchronous audio communication (AAC) with lightweight tools for inserting content, adjusting pauses, and correcting transcript errors. Qualitative and quantitative results suggest that novice audio producers, such as high school students, experience decreased mental workload when using SimpleSpeech to produce audio messages than without editing. The linguistic formality in SimpleSpeech messages was also studied, and found to form a middle ground between oral and written media. Our findings on editable voice messages show new implications for the optimal design and use cases of AAC systems.
更多查看译文
关键词
Speech editing, transcription-based editing, asynchronous audio communication
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络