Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss
Authors:
- Qian ZhangQZQian Zhang
- Han LuHLHan Lu
- Hasim SakHSHasim Sak
- Anshuman TripathiATAnshuman Tripathi
- Erik McDermottEMErik McDermott
- Stephen KooSKStephen Koo
- Shankar KumarSKShankar Kumar
Top Cited Papers
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
No abstract availableThis publication has 14 references indexed in Scilit:
- Very Deep Self-Attention Networks for End-to-End Speech Recognition2019
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition2019
- Self-attention Aligner: A Latency-control End-to-end Model for ASR Using Self-attention Network and Chunk-hopping2019
- Self-Attentional Acoustic Models2018
- A Time-Restricted Self-Attention Layer for ASR2018
- Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer2017
- Streaming small-footprint keyword spotting using sequence-to-sequence models2017
- Recurrent Neural Aligner: An Encoder-Decoder Neural Network Model for Sequence to Sequence Mapping2017
- Towards Better Decoding and Language Model Integration in Sequence to Sequence Models2017
- Connectionist temporal classification2006