REVIEW 3 cited by
Towards Improved Speech Recognition through Optimized Synthetic Data Generation
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
Towards Improved Speech Recognition through Optimized Synthetic Data Generation
read the original abstract
Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using a state-of-the-art text-to-speech model with voice cloning capabilities. Our goal is to achieve automatic speech recognition (ASR) performance comparable to models trained on real data. We explore ways to optimize synthetic data generation through finetuning, filtering and evaluation, and its use for training an end-to-end encoder-decoder ASR model. Experiments were conducted using two datasets of spontaneous, conversational speech in Qu\'ebec French. We show that improving data generation leads to large improvements in the final ASR system trained on synthetic data.
Forward citations
Cited by 3 Pith papers
-
When Synthetic Speech Is All You Have: Better Call GRPO
On synthetic banking speech alone, GRPO cuts ASR WER 40% relative to SFT (36.71%→22.09%) by improving stopping calibration and attention anchoring to audio.
-
How to Leverage Synthetic Speech for LLM-Based ASR Systems?
Layer-wise pooling plus RIR-augmented synthetic speech matches a 100%-real ASR baseline with only 25% real data (13.6 h) and beats it at higher real fractions.
-
How to Leverage Synthetic Speech for LLM-Based ASR Systems?
Layer selection plus RIR augmentation on synthetic speech matches full real-data ASR performance using 25% real speech in SLAM-ASR.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.