RED-ACE: Robust Error Detection for ASR using Confidence Embeddings
Gekhman, Zorik, Zverinski, Dina, Mallinson, Jonathan, Beryozkin, Genady
–arXiv.org Artificial Intelligence
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 propose to 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.
arXiv.org Artificial Intelligence
Oct-26-2022
- Country:
- Oceania > Australia
- Queensland > Brisbane (0.04)
- New South Wales > Sydney (0.04)
- North America
- Dominican Republic (0.04)
- United States
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California > Los Angeles County
- Long Beach (0.04)
- Minnesota > Hennepin County
- Canada
- Ontario > Toronto (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- Europe
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Poland > Greater Poland Province
- Poznań (0.04)
- Belgium > Flanders
- Antwerp Province > Antwerp (0.04)
- Spain > Catalonia
- Asia > China
- Oceania > Australia
- Genre:
- Research Report
- New Finding (0.93)
- Experimental Study (0.93)
- Research Report
- Industry:
- Information Technology (0.47)
- Technology:
- Information Technology > Artificial Intelligence
- Speech > Speech Recognition (1.00)
- Natural Language (1.00)
- Machine Learning > Neural Networks (0.94)
- Information Technology > Artificial Intelligence