5 papers
Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs
Ke-Han Lu, Keqi Deng, Ruchao Fan +2
Speech large language models (Speech LLMs) typically encode speech into sequences far longer than text, creating a major efficiency bottleneck during autoregressive decoding. A com…
Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving
Ruchao Fan, Yiming Wang, Rui Zhao +10
Speech-LLM integration has shown promising results by leveraging extensive textual pretraining, yet its specific benefits for automatic speech recognition (ASR) remain unclear. We…
Interleaved Speech-Text Language Models for Simple Streaming Text-to-Speech Synthesis
Yifan Yang, Shujie Liu, Jinyu Li +10
This paper introduces Interleaved Speech-Text Language Model (IST-LM) for zero-shot streaming Text-to-Speech (TTS). Unlike many previous approaches, IST-LM is directly trained on i…
AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM
Ruchao Fan, Bo Ren, Yuxuan Hu +3
Integrating speech into LLM (speech-LLM) has gaining increased attention recently. The mainstream solution is to connect a well-trained speech encoder and LLM with a neural adapter…
CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation
Rui Zhao, Jinyu Li, Ruchao Fan +1
Models for streaming speech translation (ST) can achieve high accuracy and low latency if they're developed with vast amounts of paired audio in the source language and written tex…