Normalization Driven Zero-shot Multi-Speaker Speech Synthesis

In this paper, we present a novel zero-shot multi-speaker speech synthesis approach (ZSM-SS) that leverages the normalization architecture and speaker encoder with non-autoregressive multi-head attention driven encoder-decoder architecture.Given an input text and a reference speech sample of an unseen person, ZSM-SS can generate speech in that person's style in a zero-shot manner. Additionally, we demonstrate how the affine parameters of normalization help in capturing the prosodic features such as energy and fundamental frequency in a disentangled fashion and can be used to generate morphed speech output. We demonstrate the efficacy of our proposed architecture on multi-speaker VCTK[1] and LibriTTS [2] datasets, using multiple quantitative metrics that measure generated speech distortion and MOS, along with speaker embedding analysis of the proposed speaker encoder model.