Improving Sequence-to-sequence Speech Recognition Training With On-the-fly Data Augmentation

Abstract

Sequence-to-Sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR). With these large and deep models overfitting remains the largest problem, outweighing performance improvements that can be obtained from better architectures. One solution to the overfitting problem is increasing the amount of available training data and the variety exhibited by the training data with the help of data augmentation. In this paper we examine the influence of three data augmentation methods on the performance of two S2S model architectures. One of the data augmentation method comes from literature, while two other methods are our own development - a time perturbation in the frequency domain and sub-sequence sampling. Our experiments on Switchboard and Fisher data show state-of-the-art performance for S2S models that are trained solely on the speech training data and do not use additional text data.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynguyen2019improving

Related papers

• Improving Code-switching And Named Entity Recognition In ASR With Speech Editing Based Data Augmentation (2023)6.34
• Enhanced Direct Speech-to-speech Translation Using Self-supervised Pre-training And Data Augmentation (2022)10.85
• Data Augmentation For End-to-end Code-switching Speech Recognition (2020)9.92
• You Do Not Need More Data: Improving End-to-end Speech Recognition By Text-to-speech Data Augmentation (2020)11.49
• Data Augmentation Methods For End-to-end Speech Recognition On Distant-talk Scenarios (2021)6.34
• A Comparison Of Speech Data Augmentation Methods Using S3PRL Toolkit (2023)0.00
• Data Augmentation Enhanced Speaker Enrollment For Text-dependent Speaker Verification (2020)0.00
• On-the-fly Aligned Data Augmentation For Sequence-to-sequence ASR (2021)9.23