Speaker Adaption with Intuitive Prosodic Features for Statistical Parametric Speech Synthesis
This is an incremental improvement for speech synthesis systems, enhancing speaker adaptation by integrating prosodic features.
The paper tackles speaker adaptation in statistical parametric speech synthesis by incorporating intuitive prosodic features like pitch, speech rate, and energy into existing frameworks, achieving better objective and subjective performance than baselines, with the utterance-level method yielding the best similarity in synthetic speech.
In this paper, we propose a method of speaker adaption with intuitive prosodic features for statistical parametric speech synthesis. The intuitive prosodic features employed in this method include pitch, pitch range, speech rate and energy considering that they are directly related with the overall prosodic characteristics of different speakers. The intuitive prosodic features are extracted at utterance-level or speaker-level, and are further integrated into the existing speaker-encoding-based and speaker-embedding-based adaptation frameworks respectively. The acoustic models are sequence-to-sequence ones based on Tacotron2. Intuitive prosodic features are concatenated with text encoder outputs and speaker vectors for decoding acoustic features.Experimental results have demonstrated that our proposed methods can achieve better objective and subjective performance than the baseline methods without intuitive prosodic features. Besides, the proposed speaker adaption method with utterance-level prosodic features has achieved the best similarity of synthetic speech among all compared methods.