Picture for Shengpeng Ji

Shengpeng Ji

Astrea: A MOE-based Visual Understanding Model with Progressive Alignment

Add code
Mar 12, 2025
Viaarxiv icon

InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training

Add code
Mar 04, 2025
Viaarxiv icon

UniCodec: Unified Audio Codec with Single Domain-Adaptive Codebook

Add code
Feb 27, 2025
Viaarxiv icon

Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis

Add code
Feb 26, 2025
Viaarxiv icon

WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models

Add code
Feb 20, 2025
Viaarxiv icon

Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model

Add code
Feb 08, 2025
Figure 1 for Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model
Figure 2 for Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model
Figure 3 for Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model
Figure 4 for Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model
Viaarxiv icon

OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios

Add code
Jan 02, 2025
Figure 1 for OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios
Figure 2 for OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios
Figure 3 for OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios
Figure 4 for OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios
Viaarxiv icon

Speech Watermarking with Discrete Intermediate Representations

Add code
Dec 18, 2024
Viaarxiv icon

WavChat: A Survey of Spoken Dialogue Models

Add code
Nov 26, 2024
Figure 1 for WavChat: A Survey of Spoken Dialogue Models
Figure 2 for WavChat: A Survey of Spoken Dialogue Models
Figure 3 for WavChat: A Survey of Spoken Dialogue Models
Figure 4 for WavChat: A Survey of Spoken Dialogue Models
Viaarxiv icon

LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval

Add code
Nov 21, 2024
Viaarxiv icon