Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications
arXiv:2010.14665
Abstract
In this paper, we summarize the application of transformer and its streamable variant, Emformer based acoustic model for large scale speech recognition applications. We compare the transformer based acoustic models with their LSTM counterparts on industrial scale tasks. Specifically, we compare Emformer with latency-controlled BLSTM (LCBLSTM) on medium latency tasks and LSTM on low latency tasks. On a low latency voice assistant task, Emformer gets 24% to 26% relative word error rate reductions (WERRs). For medium latency scenarios, comparing with LCBLSTM with similar model size and latency, Emformer gets significant WERR across four languages in video captioning datasets with 2-3 times inference real-time factors reduction.
arXiv commentsubmitted to ICASSP2021
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Neural Machine Translation by Jointly Learning to Align and Translate
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Sequence Transduction with Recurrent Neural Networks
- A Comparative Study on Transformer vs RNN in Speech Applications
- Conformer: Convolution-augmented Transformer for Speech Recognition
- Transformer-based Acoustic Modeling for Hybrid Speech Recognition
- Feedforward Sequential Memory Neural Networks without Recurrent Feedback
- Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition
- From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition
- Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces