pith. sign in

arxiv: 2209.06337 · v1 · pith:5GXLHHBG · submitted 2022-09-13 · eess.AS · cs.SD· q-bio.QM

Deep Speech Synthesis from Articulatory Representations

pith:5GXLHHBGopen to challenge →

classification eess.AS cs.SDq-bio.QM
keywords articulatorysynthesisspeechtaskdeephumanmodelsachieve
0
0 comments X
read the original abstract

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 research, as the articulatory space is compact, smooth, and interpretable. Current works have highlighted the potential for deep learning models to perform articulatory synthesis. However, it remains unclear whether these models can achieve the efficiency and fidelity of the human speech production system. To help bridge this gap, we propose a time-domain articulatory synthesis methodology and demonstrate its efficacy with both electromagnetic articulography (EMA) and synthetic articulatory feature inputs. Our model is computationally efficient and achieves a transcription word error rate (WER) of 18.5% for the EMA-to-speech task, yielding an improvement of 11.6% compared to prior work. Through interpolation experiments, we also highlight the generalizability and interpretability of our approach.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.