REVIEW 2 cited by
Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition
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
Although deep learning-based end-to-end Automatic Speech Recognition (ASR) has shown remarkable performance in recent years, it suffers severe performance regression on test samples drawn from different data distributions. Test-time Adaptation (TTA), previously explored in the computer vision area, aims to adapt the model trained on source domains to yield better predictions for test samples, often out-of-domain, without accessing the source data. Here, we propose the Single-Utterance Test-time Adaptation (SUTA) framework for ASR, which is the first TTA study on ASR to our best knowledge. The single-utterance TTA is a more realistic setting that does not assume test data are sampled from identical distribution and does not delay on-demand inference due to pre-collection for the batch of adaptation data. SUTA consists of unsupervised objectives with an efficient adaptation strategy. Empirical results demonstrate that SUTA effectively improves the performance of the source ASR model evaluated on multiple out-of-domain target corpora and in-domain test samples.
Forward citations
Cited by 2 Pith papers
-
DHAuDS: A Dynamic and Heterogeneous Audio Benchmark for Test-Time Adaptation
DHAuDS is a new audio benchmark that corrupts four existing datasets with dynamically varying and diverse acoustic noise, and evaluates three classifiers under test-time adaptation.
-
An Investigation of Test-time Adaptation for Audio Classification under Background Noise
A modified CoNMix method achieved the lowest error rates for audio classification under background noise, but the comparison is confounded and the method was tuned on the test set.
Discussion (0). Sign in to comment.