HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis
This work addresses the problem of slow and less robust zero-shot speech synthesis for text-to-speech and voice conversion applications, representing a significant advance rather than an incremental improvement.
The paper tackles the limitations of LLM-based speech synthesis, such as slow inference and lack of robustness, by proposing HierSpeech++, a hierarchical variational inference model for zero-shot speech synthesis. It achieves human-level quality, outperforming LLM-based and diffusion-based models in naturalness and speaker similarity.
Large language models (LLM)-based speech synthesis has been widely adopted in zero-shot speech synthesis. However, they require a large-scale data and possess the same limitations as previous autoregressive speech models, including slow inference speed and lack of robustness. This paper proposes HierSpeech++, a fast and strong zero-shot speech synthesizer for text-to-speech (TTS) and voice conversion (VC). We verified that hierarchical speech synthesis frameworks could significantly improve the robustness and expressiveness of the synthetic speech. Furthermore, we significantly improve the naturalness and speaker similarity of synthetic speech even in zero-shot speech synthesis scenarios. For text-to-speech, we adopt the text-to-vec framework, which generates a self-supervised speech representation and an F0 representation based on text representations and prosody prompts. Then, HierSpeech++ generates speech from the generated vector, F0, and voice prompt. We further introduce a high-efficient speech super-resolution framework from 16 kHz to 48 kHz. The experimental results demonstrated that the hierarchical variational autoencoder could be a strong zero-shot speech synthesizer given that it outperforms LLM-based and diffusion-based models. Moreover, we achieved the first human-level quality zero-shot speech synthesis. Audio samples and source code are available at https://github.com/sh-lee-prml/HierSpeechpp.