Zhizheng Wu

Although Speech Large Language Models have achieved notable progress, a substantial modality reasoning gap remains: their reasoning performance on speech inputs is markedly weaker than on text. This gap could be associated with representational drift across Transformer layers and behavior deviati...

Multilingual speech foundation models such as Whisper are trained on web-scale data, where data for each language consists of a myriad of regional varieties. However, different regional varieties often employ different scripts to write the same language, rendering speech recognition output also s...

Voice imitation aims to transform source speech to match a reference speaker’s timbre and speaking style while preserving linguistic content. A straightforward approach is to train on triplets of (source, reference, target) , where source and target share the same content but target matches the r...