| Paper ID | SPE-2.4 |
| Paper Title |
ECHO STATE SPEECH RECOGNITION |
| Authors |
Harsh Shrivastava, Georgia Institute of Technology, United States; Ankush Garg, Yuan Cao, Yu Zhang, Tara N. Sainath, Google, United States |
| Session | SPE-2: Speech Recognition 2: Neural transducer Models 2 |
| Location | Gather.Town |
| Session Time: | Tuesday, 08 June, 13:00 - 13:45 |
| Presentation Time: | Tuesday, 08 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Speech Processing: [SPE-GASR] General Topics in Speech Recognition |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
We propose automatic speech recognition (ASR) models inspired by echo state network (ESN) , in which a subset of recurrent neural networks (RNN) layers in the models are randomly initialized and untrained. Our study focuses on RNN-T and Conformer models, and we show that model quality does not drop even when the decoder is fully randomized. What is more, such models can be trained more efficiently as the decoders do not require to be updated. By contrast, randomizing encoders hurts model quality, indicating that optimizing encoders and learn proper representations for acoustic inputs are more vital for speech recognition. Overall, we challenge the common practice of training ASR models for all components, and demonstrate that ESN-based models can perform equally well but enable more efficient training and storage than fully-trainable counterparts. |
