Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Revisiting Interpolation Augmentation for Speech-to-Text Generation

About

Speech-to-text (S2T) generation systems frequently face challenges in low-resource scenarios, primarily due to the lack of extensive labeled datasets. One emerging solution is constructing virtual training samples by interpolating inputs and labels, which has notably enhanced system generalization in other domains. Despite its potential, this technique's application in S2T tasks has remained under-explored. In this paper, we delve into the utility of interpolation augmentation, guided by several pivotal questions. Our findings reveal that employing an appropriate strategy in interpolation augmentation significantly enhances performance across diverse tasks, architectures, and data scales, offering a promising avenue for more robust S2T systems in resource-constrained settings.

Chen Xu, Jie Wang, Xiaoqian Liu, Qianqian Dong, Chunliang Zhang, Tong Xiao, Jingbo Zhu, Dapeng Man, Wu Yang• 2024

Related benchmarks

TaskDatasetResultRank
Automatic Speech RecognitionLibriSpeech (test-other)
WER44.76
966
Automatic Speech RecognitionLibriSpeech (dev-other)
WER43.89
411
Automatic Speech RecognitionLibriSpeech 960h (test-other)
WER7.51
81
Automatic Speech RecognitionAISHELL-1 (test)--
71
Automatic Speech RecognitionLibriSpeech 960h (test-clean)
WER0.0301
53
Automatic Speech RecognitionLibriSpeech 960h (dev-other)
WER7.61
50
Speech TranslationMuST-C EN-DE (test-COMMON)
BLEU27.5
41
Automatic Speech RecognitionLibriSpeech 960h clean (dev)
WER2.91
25
Speech TranslationMuST-C en-de (dev)
BLEU26.92
14
Automatic Speech RecognitionLibriSpeech clean 10h (dev)
Word Error Rate0.2834
2
Showing 10 of 15 rows

Other info

Code

Follow for update