Improved Regularization Techniques For End-to-end Speech Recognition

Abstract

Regularization is important for end-to-end speech models, since the models are highly flexible and easy to overfit. Data augmentation and dropout has been important for improving end-to-end models in other domains. However, they are relatively under explored for end-to-end speech models. Therefore, we investigate the effectiveness of both methods for end-to-end trainable, deep speech recognition models. We augment audio data through random perturbations of tempo, pitch, volume, temporal alignment, and adding random noise.We further investigate the effect of dropout when applied to the inputs of all layers of the network. We show that the combination of data augmentation and dropout give a relative performance improvement on both Wall Street Journal (WSJ) and LibriSpeech dataset of over 20%. Our model performance is also competitive with other end-to-end speech models on both datasets.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhou2017improved

Related papers

• Population Based Training For Data Augmentation And Regularization In Speech Recognition (2020)0.00
• Exploiting Semi-supervised Training Through A Dropout Regularization In End-to-end Speech Recognition (2019)6.34
• Dropout Regularization For Self-supervised Learning Of Transformer Encoder Speech Representation (2021)4.52
• Macro-block Dropout For Improved Regularization In Training End-to-end Speech Recognition Models (2022)0.00
• You Do Not Need More Data: Improving End-to-end Speech Recognition By Text-to-speech Data Augmentation (2020)11.49
• Subword Regularization: An Analysis Of Scalability And Generalization For End-to-end Automatic Speech Recognition (2020)5.24
• Data Augmentation Methods For End-to-end Speech Recognition On Distant-talk Scenarios (2021)6.34
• Improving Sequence-to-sequence Speech Recognition Training With On-the-fly Data Augmentation (2019)0.00