2 papers
eess.AS2025
Bridging the Modality Gap: Softly Discretizing Audio Representation for LLM-based Automatic Speech Recognition
Mu Yang, Szu-Jui Chen, Jiamin Xie +1
One challenge of integrating speech input with large language models (LLMs) stems from the discrepancy between the continuous nature of audio data and the discrete token-based para…
eess.AS2025
Rethinking Speaker Embeddings for Speech Generation: Sub-Center Modeling for Capturing Intra-Speaker Diversity
Ismail Rasim Ulgen, John H. L. Hansen, Carlos Busso +1
Modeling the rich prosodic variations inherent in human speech is essential for generating natural-sounding speech. While speaker embeddings are commonly used as conditioning input…