Shengpeng Ji
25 papers · 2024–2026 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (50) π Conference Polyglot Β· Silver π¬ Deep Specialist (12) π€ Dynamic Duo (22)
ποΈ
Keyword Collector
(131)
β
The Questioner
β‘
Prolific Year Β· Absurd
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(20)
Core AI
(19)
Deep Learning
(16)
Speech & Audio
(14)
Machine Learning
(12)
Synthesis
(10)
Models
(9)
Learning Types Β· Deep Learning
(8)
Natural Language Processing
(6)
Learning Types Β· Machine Learning
(6)
Application Areas
(4)
Core Methods
(4)
Generation
(4)
Architectures
(3)
Recognition
(3)
Keywords
speech synthesis
(5)
vector quantization
(4)
zero-shot learning
(4)
speech processing
(3)
multimodal learning
(3)
multimodal representation
(3)
contrastive learning
(3)
generative model
(3)
spoken dialogue system
(3)
prosody transfer
(2)
speech language model
(2)
speaker cloning
(2)
speech generation
(2)
cross-modal generalization
(2)
discrete representation
(2)
retrieval-augmented generation
(2)
speech recognition
(2)
automatic speech recognition
(2)
spoken dialogue
(2)
spoken dialogue model
(2)
Papers
Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models
ACL 2026
VoxMind: An End-to-End Agentic Spoken Dialogue System
ACL 2026
CART: A Generative Cross-Modal Retrieval Framework With Coarse-To-Fine Semantic Modeling
ACL 2025
ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control
ACL 2025
Enhancing Multimodal Unified Representations for Cross Modal Generalization
ACL 2025
GTA: Towards Generative Text-To-Audio Retrieval via Multi-Scale Tokenizer
Interspeech 2025
InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training
ACL 2025
InteractSpeech: A Speech Dialogue Interaction Corpus for Spoken Dialogue Model
EMNLP 2025
IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models
ICML 2025
Language-Codec: Bridging Discrete Codec Representations and Speech Language Models
ACL 2025
OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces
ICLR 2025
OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup
ICLR 2025
Open-set Cross Modal Generalization via Multimodal Unified Representation
ICCV 2025
Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching
ACL 2025
SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language
CVPR 2025
Speech Watermarking with Discrete Intermediate Representations
AAAI 2025
T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback
ACL 2025
UniCodec: Unified Audio Codec with Single Domain-Adaptive Codebook
ACL 2025
VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words?
ICLR 2025
VoxpopuliTTS: a large-scale multilingual TTS corpus for zero-shot speech generation
COLING 2025
WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models
ACL 2025
WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
ICLR 2025
AudioVSR: Enhancing Video Speech Recognition with Audio Data
EMNLP 2024
Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
ICLR 2024
MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech
ACL 2024