Dynamic Layer Normalization For Adaptive Neural Acoustic Modeling In Speech Recognition

Abstract

Layer normalization is a recently introduced technique for normalizing the activities of neurons in deep neural networks to improve the training speed and stability. In this paper, we introduce a new layer normalization technique called Dynamic Layer Normalization (DLN) for adaptive neural acoustic modeling in speech recognition. By dynamically generating the scaling and shifting parameters in layer normalization, DLN adapts neural acoustic models to the acoustic variability arising from various factors such as speakers, channel noises, and environments. Unlike other adaptive acoustic models, our proposed approach does not require additional adaptation data or speaker information such as i-vectors. Moreover, the model size is fixed as it dynamically generates adaptation parameters. We apply our proposed DLN to deep bidirectional LSTM acoustic models and evaluate them on two benchmark datasets for large vocabulary ASR experiments: WSJ and TED-LIUM release 2. The experimental results sho

Stats

• citations34
• S2 citations—
• github stars0
• HF likes0
• heat score11.58
• arxiv keykim2017dynamic

Related papers

• Attentive Batch Normalization For Lstm-based Acoustic Modeling Of Speech Recognition (2020)0.00
• Batch-normalized Joint Training For Dnn-based Distant Speech Recognition (2017)8.82
• Linear Networks Based Speaker Adaptation For Speech Synthesis (2018)6.34
• Scaling And Bias Codes For Modeling Speaker-adaptive Dnn-based Speech Synthesis Systems (2018)6.34
• Layer-wise Fast Adaptation For End-to-end Multi-accent Speech Recognition (2022)9.76
• Run-time Adaptation Of Neural Beamforming For Robust Speech Dereverberation And Denoising (2024)0.00
• Dynamic Sparsity Neural Networks For Automatic Speech Recognition (2020)0.00
• Layer-aware TDNN: Speaker Recognition Using Multi-layer Features From Pre-trained Models (2024)0.00