AMNet: An Acoustic Model Network for Enhanced Mandarin Speech Synthesis
This work addresses the problem of generating high-quality and expressive Mandarin speech for speech synthesis applications, representing an incremental improvement over existing methods.
The paper tackles the challenge of local context modeling in Mandarin speech synthesis by proposing AMNet, which incorporates phrase structure annotation and local convolution modules, resulting in superior Mean Opinion Scores, lower Mel Cepstral Distortion, and improved fundamental frequency fitting compared to baseline models.
This paper presents AMNet, an Acoustic Model Network designed to improve the performance of Mandarin speech synthesis by incorporating phrase structure annotation and local convolution modules. AMNet builds upon the FastSpeech 2 architecture while addressing the challenge of local context modeling, which is crucial for capturing intricate speech features such as pauses, stress, and intonation. By embedding a phrase structure parser into the model and introducing a local convolution module, AMNet enhances the model's sensitivity to local information. Additionally, AMNet decouples tonal characteristics from phonemes, providing explicit guidance for tone modeling, which improves tone accuracy and pronunciation. Experimental results demonstrate that AMNet outperforms baseline models in subjective and objective evaluations. The proposed model achieves superior Mean Opinion Scores (MOS), lower Mel Cepstral Distortion (MCD), and improved fundamental frequency fitting $F0 (R^2)$, confirming its ability to generate high-quality, natural, and expressive Mandarin speech.