Total: 1
Fusing speech into a pre-trained language model (SpeechLM) usually suffers from the inefficient encoding of long-form speech and catastrophic forgetting of pre-trained text modality. We propose SSR (Segmented Speech Representation Connector) for better modality fusion. Leveraging speech-text alignments, our approach segments and compresses speech features to match the granularity of text embeddings. Additionally, we introduce a two-stage training pipeline that includes the distillation and fine-tuning phases to mitigate catastrophic forgetting. SSR outperforms existing mechanisms for speech-text modality fusion, consistently achieving better speech understanding (e.g., +10 accuracy on StoryCloze and +20 on Speech-MMLU) while preserving pre-trained text ability.