paper-with-me

홈 › Papers

Deep Speech Synthesis from Multimodal Articulatory Representations

2024-12-17 · Peter Wu, Bohan Yu, Kevin Scheck, Alan W Black, Aditi S. Krishnapriyan, Irene Y. Chen, Tanja Schultz, Shinji Watanabe, Gopala K. Anumanchipalli

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.

📄 PDF Abstract BibTeX arXiv:2412.13387

Code (0)

등록된 구현이 없습니다.

Tasks

Speech SynthesisTransfer Learning

Similar Papers 제목 키워드 기반

Deep Speech Synthesis from Articulatory Representations

2022-09-13 · Peter Wu, Shinji Watanabe, Louis Goldstein, Alan W Black 외

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 Synthesis

Deep Speech Synthesis from MRI-Based Articulatory Representations

2023-07-05 · Peter Wu, Tingle Li, Yijing Lu, Yubin Zhang 외

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 Synthesis

Articulation GAN: Unsupervised modeling of articulatory learning

2022-10-27 · Gašper Beguš, Alan Zhou, Peter Wu, Gopala K Anumanchipalli

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 Synthesis

Speaker-Independent Acoustic-to-Articulatory Speech Inversion

2023-02-14 · Peter Wu, Li-Wei Chen, Cheol Jun Cho, Shinji Watanabe 외

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…

Resynthesis

Manipulation of oral cancer speech using neural articulatory synthesis

2022-03-31 · Bence Mark Halpern, Teja Rebernik, Thomas Tienkamp, Rob van Son 외

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