Semi-supervised Adaptation of Assistant Based Speech Recognition Models for different Approach Areas
| Autor: | Gerald Siol, Heiko Ehr, Petr Motlicek, Matthias Kleinert, Aneta Cerna, Mittul Singh, Christian Kern, Hartmut Helmke, Youssef Oualil, Ajay Srinivasamurthy, Dietrich Klakow |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
050210 logistics & transportation
Computer science Speech recognition 05 social sciences Unsupervised Learning 020206 networking & telecommunications Automatic Speech Recognition 02 engineering and technology Command Prediction Model Machine Learning Assistant Based Speech Recognition 0502 economics and business 0202 electrical engineering electronic engineering information engineering Lotsenassistenz Adaptation (computer science) |
| Zdroj: | 2018 IEEE/AIAA 37th Digital Avionics Systems Conference (DASC). |
| DOI: | 10.1109/dasc.2018.8569879 |
| Popis: | Air Navigation Service Providers (ANSPs) replace paper flight strips through different digital solutions. The instructed com-mands from an air traffic controller (ATCos) are then available in computer readable form. However, those systems require manual controller inputs, i.e. ATCos workload increases. The Active Listening Assistant (AcListant®) project has shown that Assistant Based Speech Recognition (ABSR) is a potential solution to reduce this additional workload. However, the development of an ABSR application for a specific target-domain usually requires a large amount of manually transcribed audio data in order to achieve task-sufficient recognition accuracies. MALORCA project developed an initial basic ABSR system and semi-automatically tailored its recognition models for both Prague and Vienna approaches by machine learning from automatically transcribed audio data. Command recognition error rates were reduced from 7.9% to under 0.6% for Prague and from 18.9% to 3.2% for Vienna. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|