Synth2Aug: Cross-domain speaker recognition with TTS synthesized speech
This work addresses the problem of limited training data for speaker recognition, which is a common challenge for researchers and developers in the speech technology domain.
This paper explores using multi-speaker Text-To-Speech (TTS) synthesized speech to augment training data for speaker recognition, particularly when few speakers are available. The study found that TTS synthesized speech improves cross-domain speaker recognition performance and can be effectively combined with multi-style training.
In recent years, Text-To-Speech (TTS) has been used as a data augmentation technique for speech recognition to help complement inadequacies in the training data. Correspondingly, we investigate the use of a multi-speaker TTS system to synthesize speech in support of speaker recognition. In this study we focus the analysis on tasks where a relatively small number of speakers is available for training. We observe on our datasets that TTS synthesized speech improves cross-domain speaker recognition performance and can be combined effectively with multi-style training. Additionally, we explore the effectiveness of different types of text transcripts used for TTS synthesis. Results suggest that matching the textual content of the target domain is a good practice, and if that is not feasible, a transcript with a sufficiently large vocabulary is recommended.