Jonathan Mallinson, Zorik Gekhman, Genady Beryozkin, Dina Zverinski
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.
ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR) systems, in order to detect transcription errors. Modern approaches usually use text-based input, comprised solely of the ASR transcription hypothesis, disregarding additional signals from the ASR model. Instead, we utilize the ASR system's word-level confidence scores for improving AED performance. Specifically, we add an ASR Confidence Embedding (ACE) layer to the AED model's encoder, allowing us to jointly encode the confidence scores and the transcribed text into a contextualized representation. Our experiments show the benefits of ASR confidence scores for AED, their complementary effect over the textual signal, as well as the effectiveness and robustness of ACE for combining these signals. To foster further research, we publish a novel AED dataset consisting of ASR outputs on the LibriSpeech corpus with annotated transcription errors. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.07172")
get_code_for_paper("2203.07172")
have("2203.07172")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.07172.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.07172)
Connect an agent — have() is free.