A CTC Triggered Siamese Network With Spatial-temporal Dropout For Speech Recognition

Abstract

Siamese networks have shown effective results in unsupervised visual representation learning. These models are designed to learn an invariant representation of two augmentations for one input by maximizing their similarity. In this paper, we propose an effective Siamese network to improve the robustness of End-to-End automatic speech recognition (ASR). We introduce spatial-temporal dropout to support a more violent disturbance for Siamese-ASR framework. Besides, we also relax the similarity regularization to maximize the similarities of distributions on the frames that connectionist temporal classification (CTC) spikes occur rather than on all of them. The efficiency of the proposed architecture is evaluated on two benchmarks, AISHELL-1 and Librispeech, resulting in 7.13% and 6.59% relative character error rate (CER) and word error rate (WER) reductions respectively. Analysis shows that our proposed approach brings a better uniformity for the trained model and enlarges the CTC spikes o

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygao2022a

Related papers

• Unsupervised Feature Learning For Speech Using Correspondence And Siamese Networks (2020)8.09
• Residual Convolutional CTC Networks For Automatic Speech Recognition (2017)0.00
• Sampling Strategies In Siamese Networks For Unsupervised Speech Representation Learning (2018)8.35
• Prosodic-enhanced Siamese Convolutional Neural Networks For Cross-device Text-independent Speaker Verification (2018)8.35
• CR-CTC: Consistency Regularization On CTC For Improved Speech Recognition (2024)6.30
• CTC Blank Triggered Dynamic Layer-skipping For Efficient Ctc-based Speech Recognition (2024)0.00
• Linguistic-enhanced Transformer With CTC Embedding For Speech Recognition (2022)2.26
• Self-attention Networks For Connectionist Temporal Classification In Speech Recognition (2019)14.55