"Pruned RNN-T for fast, memory-efficient ASR training."

Fangjun Kuang et al. (2022)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2206.13236

access: open

type: Informal or Other Publication

metadata version: 2023-05-19

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2206-13236
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2206-13236
Fangjun Kuang, Liyong Guo, Wei Kang, Long Lin, Mingshuang Luo, Zengwei Yao, Daniel Povey:
Pruned RNN-T for fast, memory-efficient ASR training. CoRR abs/2206.13236 (2022)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.