Search Results for author:
Found 2 papers, 0 papers with code
Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy?
Decoder-only discrete-token language models have recently achieved significant success in automatic speech recognition.
Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing
Moreover, for ASR, it benefits from initializing DMLM from a pretrained LLM, and from a codebook derived from Whisper activations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
