Hung-Yi Lee, Yung-Sung Chuang, Shun-Po Chuang, Chih-Chiang Chang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We study the possibilities of building a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC), and use CTC-based automatic speech recognition as an auxiliary task to improve the performance. CTC's success on translation is counter-intuitive due to its monotonicity assumption, so we analyze its reordering capability. Kendall's tau distance is introduced as the quantitative metric, and gradientbased visualization provides an intuitive way to take a closer look into the model. Our analysis shows that transformer encoders have the ability to change the word order and points out the future research direction that worth being explored more on non-autoregressive speech translation. 1 * Contributed equally. 1 The source code is available. See Appendix A.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2105.04840")
get_code_for_paper("2105.04840")
have("2105.04840")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2105.04840.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2105.04840)
Connect an agent — have() is free.