Speaking style adaptation in Text-To-Speech synthesis using Sequence-to-sequence models with attention
arXiv:1810.12051
Abstract
Currently, there are increasing interests in text-to-speech (TTS) synthesis to use sequence-to-sequence models with attention. These models are end-to-end meaning that they learn both co-articulation and duration properties directly from text and speech. Since these models are entirely data-driven, they need large amounts of data to generate synthetic speech with good quality. However, in challenging speaking styles, such as Lombard speech, it is difficult to record sufficiently large speech corpora. Therefore, in this study we propose a transfer learning method to adapt a sequence-to-sequence based TTS system of normal speaking style to Lombard style. Moreover, we experiment with a WaveNet vocoder in synthesis of Lombard speech. We conducted subjective evaluations to assess the performance of the adapted TTS systems. The subjective evaluation results indicated that an adaptation system with the WaveNet vocoder clearly outperformed the conventional deep neural network based TTS system in synthesis of Lombard speech.
arXiv comment5 pages, 5 figures. Submitted to ICASSP 2019
References in corpus (9)
- Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
- Deep Voice: Real-time Neural Text-to-Speech
- Neural Voice Cloning with a Few Samples
- Tacotron: Towards End-to-End Speech Synthesis
- ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
- Fitting New Speakers Based on a Short Untranscribed Sample
- Semi-Supervised Training for Improving Data Efficiency in End-to-End Speech Synthesis
- Linear networks based speaker adaptation for speech synthesis
- Multimodal speech synthesis architecture for unsupervised speaker adaptation