conftrace_

discrete token

28 papers

Explore in graph

Co-occurring keywords

vector quantization (257) speech synthesis (757) generative model (2892) discrete representation (74) audio generation (76) human motion generation (61) variational autoencoder (1288) image generation (2073) continuous representation (32) speech tokenization (11)

Papers

HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting AAAI 2025
DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding ICCV 2025
SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation ACL 2025
Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression CVPR 2025
Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation ICCV 2025
Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis ICCV 2025
Analyzing and Mitigating Inconsistency in Discrete Speech Tokens for Neural Codec Language Models ACL 2025
Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs EMNLP 2025
SDformer: Similarity-driven Discrete Transformer For Time Series Generation NIPS 2024
Children’s Speech Recognition through Discrete Token Enhancement INTERSPEECH 2024
TokSing: Singing Voice Synthesis based on Discrete Tokens INTERSPEECH 2024
High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model INTERSPEECH 2024
Genhancer: High-Fidelity Speech Enhancement via Generative Modeling on Discrete Codec Tokens INTERSPEECH 2024
Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling CVPR 2024
Evaluating Text-to-Speech Synthesis from a Large Discrete Token-based Speech Language Model COLING 2024
LLM Knows Body Language, Too: Translating Speech Voices into Human Gestures ACL 2024
MoMask: Generative Masked Modeling of 3D Human Motions CVPR 2024
Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99% NIPS 2024
From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion NIPS 2023
Human Pose As Compositional Tokens CVPR 2023
TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition INTERSPEECH 2023
High-Fidelity Audio Compression with Improved RVQGAN NIPS 2023
Muse: Text-To-Image Generation via Masked Generative Transformers ICML 2023
All in Tokens: Unifying Output Space of Visual Tasks via Soft Token ICCV 2023
MotionLM: Multi-Agent Motion Forecasting as Language Modeling ICCV 2023