Deep Speech Synthesis from Multimodal Articulatory Representations
The amount of articulatory data available for training deep learning models is much less compared to acoustic speech data. In order to improve articulatory-to-acoustic synthesis performance in these low-resource settings, we propose a multimodal pre-training framework. On single-speaker speech synthesis tasks from real-time magnetic resonance imaging and surface electromyography inputs, the intelligibility of synthesized outputs improves noticeably. For example, compared to prior work, utilizing our proposed transfer learning methods improves the MRI-to-speech performance by 36% word error rate. In addition to these intelligibility results, our multimodal pre-trained models consistently outperform unimodal baselines on three objective and subjective synthesis quality metrics.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech SynthesisTransfer LearningSimilar Papers 제목 키워드 기반
Deep Speech Synthesis from Articulatory Representations
In the articulatory synthesis task, speech is synthesized from input features containing information about the physical behavior of the human vocal tract. This task provides a promising direction for speech synthesis res…
Speech SynthesisDeep Speech Synthesis from MRI-Based Articulatory Representations
In this paper, we study articulatory synthesis, a speech synthesis method using human vocal tract information that offers a way to develop efficient, generalizable and interpretable synthesizers. While recent advances ha…
Computational EfficiencyDenoisingSpeech SynthesisArticulation GAN: Unsupervised modeling of articulatory learning
Generative deep neural networks are widely used for speech synthesis, but most existing models directly generate waveforms or spectral outputs. Humans, however, produce speech by controlling articulators, which results i…
Generative Adversarial NetworkSpeech SynthesisSpeaker-Independent Acoustic-to-Articulatory Speech Inversion
To build speech processing methods that can handle speech as naturally as humans, researchers have explored multiple ways of building an invertible mapping from speech to an interpretable space. The articulatory space is…
ResynthesisManipulation of oral cancer speech using neural articulatory synthesis
We present an articulatory synthesis framework for the synthesis and manipulation of oral cancer speech for clinical decision making and alleviation of patient stress. Objective and subjective evaluations demonstrate tha…
Decision Making