conftrace_

cross-modality pre-training

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

unpaired audio-text data (1) foundation model fusion (1) chernoff distance (1) singing voice deepfake (1) audio encoder (1) source attribution (1) multimodal foundation model (1) audio embedding (1) text embedding (1) automatic speech recognition (1)

Papers

Text-Enhanced Audio Encoder for Large Language Model based Speech Recognition via Cross-Modality Pre-training with Unpaired Audio-Text Data Interspeech 2025 Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Interspeech 2025