ConversationalVoice: Full-Duplex Speech Data from Real Conversations through Source-Faithful Reconstruction and Conversation-Grounded Expansion
Conversational Voice, a pipeline that converts real two-speaker excerpts into three complementary training-data artifacts, is presented, a pipeline that converts real two-speaker excerpts into three complementary training-data artifacts.
Richard Yucheng He, Bao-Dong Cao, Chen Xu et al.
· 1 citation