2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSPE-10.4
Paper Title DEVELOPING REAL-TIME STREAMING TRANSFORMER TRANSDUCER FOR SPEECH RECOGNITION ON LARGE-SCALE DATASET
Authors Xie Chen, Yu Wu, Zhenghao Wang, Shujie Liu, Jinyu Li, Microsoft, United States
SessionSPE-10: Speech Recognition 4: Transformer Models 2
LocationGather.Town
Session Time:Tuesday, 08 June, 16:30 - 17:15
Presentation Time:Tuesday, 08 June, 16:30 - 17:15
Presentation Poster
Topic Speech Processing: [SPE-LVCR] Large Vocabulary Continuous Recognition/Search
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Recently, Transformer based end-to-end models have achieved great success in many areas including speech recognition. However, compared to LSTM models, the heavy computational cost of the Transformer during inference is a potential issue to prevent their applications. In this work, we explored the potential of Transformer Transducer (T-T) models for the fist pass decoding with low latency and fast speed on a large-scale dataset. We combine the idea of Transformer-XL and chunk-wise streaming processing to design a streamable Transformer Transducer model. We demonstrate that T-T outperforms the hybrid model, RNN Transducer (RNN-T), and streaming Transformer attention-based encoder-decoder model in the streaming scenario. Furthermore, the runtime cost and latency can be optimized with a relatively small look-ahead.