UTTERANCE DETERMINATION PROGRAM, UTTERANCE DETERMINATION METHOD, AND UTTERANCE DETERMINATION DEVICE

摘要

To appropriately determine a user's utterance when detection of an utterance section is resumed even when detection of the utterance section is stopped while synthesized speech is output from a speaker.SOLUTION: A signal-to-noise ratio is calculated using a background noise estimated using a divided signal of a frame positioned before a determination target frame for the determination target frame among the plurality of frames each including the divided signal of a predetermined length. Whether or not the determination target frame is a frame corresponding to an utterance section is determined when the determination target frame corresponds to a sound section on the basis of the signal-to-noise ratio, and the determination target frame is a non-synthesized speech section. The determination is made based on a pitch gain indicating the strength of the periodicity of the divided signal of the determination target frame. The background noise is estimated based on the divided signal of the frame corresponding to a silent section of a synthesized speech section and the divided signal of the frame corresponding to the silent section of the non-synthesized speech section.SELECTED DRAWING: Figure 8