Neural Generation of Dialogue Response Timings
This work addresses the challenge of making spoken dialogue systems more natural for users, though it appears incremental as it builds on existing neural methods for timing simulation.
The paper tackled the problem of generating natural response timings in spoken dialogue by proposing neural models that simulate response offset distributions based on dialogue context, and showed through human listening tests that certain timings are perceived as more natural, potentially increasing interaction naturalness in dialogue systems.
The timings of spoken response offsets in human dialogue have been shown to vary based on contextual elements of the dialogue. We propose neural models that simulate the distributions of these response offsets, taking into account the response turn as well as the preceding turn. The models are designed to be integrated into the pipeline of an incremental spoken dialogue system (SDS). We evaluate our models using offline experiments as well as human listening tests. We show that human listeners consider certain response timings to be more natural based on the dialogue context. The introduction of these models into SDS pipelines could increase the perceived naturalness of interactions.