Article

Domain Adversarial Training for German Accented Speech Recognition (de)

Authors

* Presenting author
Day / Time: 09.03.2023, 10:00-10:20
Room: Saal Y8
Typ: Vortrag (strukturierte Sitzung)
Session: Speech Processing, Anonymization and Machine Learning for Medical and Social Good
Abstract: Accented speech poses difficulties to automatic speech recognition (ASR) models because of its phonetic differences with the speech corpora the models were trained on. This issue can be addressed by performing domain adversarial training (DAT) with an accent classifier, where the ASR model is encouraged to discard accent information. In this study, we perform a comprehensive evaluation of this training method with the current state-of-the-art ASR model for German speech, the Conformer Transducer. We analyze the effect of important parameters, such as when to branch out the classifier or how to weight the two tasks, from which we draw several conclusions that can serve as a guideline for future experiments with this framework.
Error

Error : E_DEPRECATED

strpos(): Passing null to parameter #1 ($haystack) of type string is deprecated

1
/kunden/431424_13355/webseiten/subdomains/app2023.daga-tagung.de/memyc/resources/OutputCompression.php, line 35
32.              */
33.             if (headers_sent()) {
34.                 $encoding = false;
35.             } elseif (strpos($HTTP_ACCEPT_ENCODING, 'x-gzip') !== false) {
36.                 $encoding = 'x-gzip';
37.             } elseif (strpos($HTTP_ACCEPT_ENCODING, 'gzip') !== false) {
38.                 $encoding = 'gzip';