Pith. sign in

REVIEW

Deep Speech Synthesis from Articulatory Representations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

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

Deep Speech Synthesis from Articulatory Representations

classification eess.AS cs.SDq-bio.QM
keywords articulatorysynthesisspeechtaskdeephumanmodelsachieve
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
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.

discussion (0)

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