Frustratingly Easy Data Augmentation for Low-Resource ASR
This paper introduces three self-contained data augmentation methods for low-resource Automatic Speech Recognition (ASR). Our techniques first generate novel text--using gloss-based replacement, random replacement, or an LLM-based approach--and then apply Text-to-Speech (TTS) to produce synthetic audio. We apply these methods, which leverage only the original annotated data, to four languages with extremely limited resources (Vatlongos, Nashta, Shinekhen Buryat, and Kakabe). Fine-tuning a pretrained Wav2Vec2-XLSR-53 model on a combination of the original audio and generated synthetic data yields significant performance gains, including a 14.3% absolute WER reduction for Nashta. The methods prove effective across all four low-resource languages and also show utility for high-resource languages like English, demonstrating their broad applicability.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech RecognitionData AugmentationSimilar Papers 제목 키워드 기반
Frustratingly Easy Uncertainty Estimation for Distribution Shift
Distribution shift is an important concern in deep image classification, produced either by corruption of the source images, or a complete change, with the solution involving domain adaptation. While the primary goal is …
Domain Adaptationimage-classificationImage ClassificationUnsupervised Domain AdaptationFrustratingly Easy Cross-Lingual Transfer for Transition-Based Dependency Parsing
TripleE: Easy Domain Generalization via Episodic Replay
Learning how to generalize the model to unseen domains is an important area of research. In this paper, we propose TripleE, and the main idea is to encourage the network to focus on training on subsets (learning with rep…
DiversityDomain GeneralizationFrustratingly Easy Neural Domain Adaptation
Popular techniques for domain adaptation such as the feature augmentation method of Daum{\'e} III (2009) have mostly been considered for sparse binary-valued features, but not for dense real-valued features such as those…
Domain AdaptationFrustratingly Easy Natural Question Answering
Existing literature on Question Answering (QA) mostly focuses on algorithmic novelty, data augmentation, or increasingly large pre-trained language models like XLNet and RoBERTa. Additionally, a lot of systems on the QA …
Data AugmentationNatural QuestionsQuestion AnsweringTransfer Learning