1 citations · 1 across the 7 of their papers we have counts for
7 papers · 1 filter
HiPLEX: Hierarchical Policy Factorization for Full Duplex Speech Language Models
Kyudan Jung, Hyunsin Park, Yoonhyung Lee +5
As human--AI interactions become more conversational, full-duplex speech language models capable of natural real-time dialogue are growing in importance. Beyond generating appropri…
Hiding Tool Latency in On-Device Cascaded Voice Agent through Speculative Execution
Kyudan Jung, Hyunsin Park, Yoonhyung Lee +5
Tool-augmented speech assistants typically serialize automatic speech recognition, large language model inference, and external tool execution. As a result, tool latency is incurre…
SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning
KiHyun Nam, Jungwoo Heo, Siu Bae +2
As audio-first agents become increasingly common in physical AI, conversational robots, and screenless wearables, audio large language models (audio-LLMs) must integrate speaker-sp…
Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS
Deokjin Seo, Gangin Park, Kihyun Nam
We present Chatterbox-Flash, a zero-shot text-to-speech model obtained by fine-tuning a pretrained autoregressive TTS decoder into a block-diffusion decoder, enabling parallel toke…
LAMB: LLM-based Audio Captioning with Modality Gap Bridging via Cauchy-Schwarz Divergence
Hyeongkeun Lee, Jongmin Choi, KiHyun Nam +1
Automated Audio Captioning aims to describe the semantic content of input audio. Recent works have employed large language models (LLMs) as a text decoder to leverage their reasoni…
Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap
KiHyun Nam, Jongmin Choi, Hyeongkeun Lee +2
Contrastive audio-language pretraining yields powerful joint representations, yet a persistent audio-text modality gap limits the benefits of coupling multimodal encoders with larg…
Disentangled Representation Learning for Environment-agnostic Speaker Recognition
KiHyun Nam, Hee-Soo Heo, Jee-weon Jung +1
This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a…