REVIEW 1 cited by
Training Neural Speech Recognition Systems with Synthetic Speech Augmentation
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
read the original abstract
Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues preventing advancements in ASR research. To address this problem, we propose to augment a natural speech dataset with synthetic speech. We train very large end-to-end neural speech recognition models using the LibriSpeech dataset augmented with synthetic speech. These new models achieve state of the art Word Error Rate (WER) for character-level based models without an external language model.
Forward citations
Cited by 1 Pith paper
-
AMuSeD: An Attentive Deep Neural Network for Multimodal Sarcasm Detection Incorporating Bi-modal Data Augmentation
A text-audio sarcasm detector using back translation and speech synthesis augmentation plus self-attention reports 81.0 F1 on MUStARD, surpassing prior three-modality baselines.
Discussion (0). Continue with ORCID to comment.