Gujarati-English Code-Switching Speech Recognition using ensemble prediction of spoken language

arXiv:2403.08011v1 Announce Type: cross
Abstract: An important and difficult task in code-switched speech recognition is to recognize the language, as lots of words in two languages can sound similar, especially in some accents. We focus on improving performance of end-to-end Automatic Speech Recognition models by conditioning transformer layers on language ID of words and character in the output in an per layer supervised manner. To this end, we propose two methods of introducing language specific parameters and explainability in the …

abstract accents arxiv automatic speech recognition code cs.ai cs.cl cs.lg english ensemble focus language languages performance prediction recognition sound speech speech recognition speech recognition models spoken transformer type words