Several recently proposed text-to-speech (TTS) models achieved to generate the speech samples with the human-level quality in the single-speaker and multi-speaker TTS scenarios with a set of pre-defined speakers.
For training a few-shot keyword spotting (FS-KWS) model, a large labeled dataset containing massive target keywords has known to be essential to generalize to arbitrary target keywords with only a few enrollment samples.
The experimental results show that fine-tuning with a disentanglement framework on a existing pre-trained model is valid and can further improve performance.
The experimental results verify the effectiveness of the proposed method in terms of naturalness, intelligibility, and speaker generalization.
In this work, we propose StyleTagging-TTS (ST-TTS), a novel expressive TTS model that utilizes a style tag written in natural language.