External Knowledge Augmented Polyphone Disambiguation Using Large Language Model
This addresses a key issue in Mandarin TTS systems for better pronunciation accuracy, but it is incremental as it applies existing LLM techniques to a specific domain problem.
The paper tackles polyphone disambiguation in Mandarin Chinese text-to-speech systems by proposing a method that uses a large language model with external knowledge, achieving improved performance over existing methods on the CPP dataset.
One of the key issues in Mandarin Chinese text-to-speech (TTS) systems is polyphone disambiguation when doing grapheme-to-phoneme (G2P) conversion. In this paper, we introduce a novel method to solve the problem as a generation task. Following the trending research of large language models (LLM) and prompt learning, the proposed method consists of three modules. Retrieval module incorporates external knowledge which is a multi-level semantic dictionary of Chinese polyphonic characters to format the sentence into a prompt. Generation module adopts the decoder-only Transformer architecture to induce the target text. Postprocess module corrects the generated text into a valid result if needed. Experimental results show that our method outperforms the existing methods on a public dataset called CPP. We also empirically study the impacts of different templates of the prompt, different sizes of training data, and whether to incorporate external knowledge.