Multilingual speech recognition and identification

From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition

Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition

Reducing Language Confusion for Code-switching Speech Recognition with Token-level Language Diarization

Locale Encoding for scalable multilingual keyword spotting models

Leveraging Multiple Sources in Automatic African American English Dialect Detection for Adults and Children