Why Your Tokenizer Fails in Information Fusion: A Timing-Aware Pre-Quantization Fusion for Video-Enhanced Audio Tokenization
Fuente:
arXiv
Saved in:
| Main Authors: | Zhang, Xiangyu, Southwell, Benjamin John, Pan, Siqi, Niu, Xinlei, Ahmed, Beena, Epps, Julien |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Why Pre-trained Models Fail: Feature Entanglement in Multi-modal Depression Detection
by: Zhang, Xiangyu, et al.
Published: (2025)
by: Zhang, Xiangyu, et al.
Published: (2025)
Zero-Shot Cognitive Impairment Detection from Speech Using AudioLLM
by: Shahin, Mostafa, et al.
Published: (2025)
by: Shahin, Mostafa, et al.
Published: (2025)
Beyond Video-to-SFX: Video to Audio Synthesis with Environmentally Aware Speech
by: Niu, Xinlei, et al.
Published: (2025)
by: Niu, Xinlei, et al.
Published: (2025)
Mamba in Speech: Towards an Alternative to Self-Attention
by: Zhang, Xiangyu, et al.
Published: (2024)
by: Zhang, Xiangyu, et al.
Published: (2024)
When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection
by: Zhang, Xiangyu, et al.
Published: (2024)
by: Zhang, Xiangyu, et al.
Published: (2024)
MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models
by: Gong, Yitian, et al.
Published: (2026)
by: Gong, Yitian, et al.
Published: (2026)
DSA-Tokenizer: Disentangled Semantic-Acoustic Tokenization via Flow Matching-based Hierarchical Fusion
by: Zhang, Hanlin, et al.
Published: (2026)
by: Zhang, Hanlin, et al.
Published: (2026)
Robust Audio-Visual Target Speaker Extraction with Emotion-Aware Multiple Enrollment Fusion
by: Jin, Zhan, et al.
Published: (2025)
by: Jin, Zhan, et al.
Published: (2025)
SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information
by: Zhang, Xiangyu, et al.
Published: (2025)
by: Zhang, Xiangyu, et al.
Published: (2025)
MelTok: 2D Tokenization for Single-Codebook Audio Compression
by: Li, Jingyi, et al.
Published: (2025)
by: Li, Jingyi, et al.
Published: (2025)
Spatial-Aware Conditioned Fusion for Audio-Visual Navigation
by: Wu, Shaohang, et al.
Published: (2026)
by: Wu, Shaohang, et al.
Published: (2026)
LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models
by: Zhao, Xiaohan, et al.
Published: (2025)
by: Zhao, Xiaohan, et al.
Published: (2025)
FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge
by: Goswami, Nabarun, et al.
Published: (2025)
by: Goswami, Nabarun, et al.
Published: (2025)
HybridVC: Efficient Voice Style Conversion with Text and Audio Prompts
by: Niu, Xinlei, et al.
Published: (2024)
by: Niu, Xinlei, et al.
Published: (2024)
Analyzing and Mitigating Inconsistency in Discrete Audio Tokens for Neural Codec Language Models
by: Liu, Wenrui, et al.
Published: (2024)
by: Liu, Wenrui, et al.
Published: (2024)
Reliability-Aware Geometric Fusion for Robust Audio-Visual Navigation
by: Liu, Teng, et al.
Published: (2026)
by: Liu, Teng, et al.
Published: (2026)
NAST: Noise Aware Speech Tokenization for Speech Language Models
by: Messica, Shoval, et al.
Published: (2024)
by: Messica, Shoval, et al.
Published: (2024)
NDVQ: Robust Neural Audio Codec with Normal Distribution-Based Vector Quantization
by: Niu, Zhikang, et al.
Published: (2024)
by: Niu, Zhikang, et al.
Published: (2024)
OMAR-RQ: Open Music Audio Representation Model Trained with Multi-Feature Masked Token Prediction
by: Alonso-Jiménez, Pablo, et al.
Published: (2025)
by: Alonso-Jiménez, Pablo, et al.
Published: (2025)
FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion
by: Chen, Shunian, et al.
Published: (2025)
by: Chen, Shunian, et al.
Published: (2025)
Audio Spatially-Guided Fusion for Audio-Visual Navigation
by: Zhou, Xinyu, et al.
Published: (2026)
by: Zhou, Xinyu, et al.
Published: (2026)
Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation
by: Wu, Yusong, et al.
Published: (2022)
by: Wu, Yusong, et al.
Published: (2022)
Rethinking Mamba in Speech Processing by Self-Supervised Models
by: Zhang, Xiangyu, et al.
Published: (2024)
by: Zhang, Xiangyu, et al.
Published: (2024)
Addressing Index Collapse of Large-Codebook Speech Tokenizer with Dual-Decoding Product-Quantized Variational Auto-Encoder
by: Guo, Haohan, et al.
Published: (2024)
by: Guo, Haohan, et al.
Published: (2024)
A Probabilistic Fusion Framework for Spoofing Aware Speaker Verification
by: Zhang, You, et al.
Published: (2022)
by: Zhang, You, et al.
Published: (2022)
CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer
by: Takeuchi, Daiki, et al.
Published: (2025)
by: Takeuchi, Daiki, et al.
Published: (2025)
DashengTokenizer: One layer is enough for unified audio understanding and generation
by: Dinkel, Heinrich, et al.
Published: (2026)
by: Dinkel, Heinrich, et al.
Published: (2026)
Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0
by: Wang, Zhiyong, et al.
Published: (2024)
by: Wang, Zhiyong, et al.
Published: (2024)
DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions
by: Niu, Shu-Tong, et al.
Published: (2024)
by: Niu, Shu-Tong, et al.
Published: (2024)
High-Fidelity Speech Enhancement via Discrete Audio Tokens
by: Lanzendörfer, Luca A., et al.
Published: (2025)
by: Lanzendörfer, Luca A., et al.
Published: (2025)
Post-Training Quantization for Audio Diffusion Transformers
by: Khandelwal, Tanmay, et al.
Published: (2025)
by: Khandelwal, Tanmay, et al.
Published: (2025)
Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion
by: Shi, Yu-Fei, et al.
Published: (2024)
by: Shi, Yu-Fei, et al.
Published: (2024)
Audio Inpainting in Time-Frequency Domain with Phase-Aware Prior
by: Balušík, Peter, et al.
Published: (2026)
by: Balušík, Peter, et al.
Published: (2026)
WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
by: Ji, Shengpeng, et al.
Published: (2024)
by: Ji, Shengpeng, et al.
Published: (2024)
MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognition
by: Wang, He, et al.
Published: (2024)
by: Wang, He, et al.
Published: (2024)
Recovering Performance in Speech Emotion Recognition from Discrete Tokens via Multi-Layer Fusion and Paralinguistic Feature Integration
by: Sun, Esther, et al.
Published: (2026)
by: Sun, Esther, et al.
Published: (2026)
LAST: Language Model Aware Speech Tokenization
by: Turetzky, Arnon, et al.
Published: (2024)
by: Turetzky, Arnon, et al.
Published: (2024)
Acoustic BPE for Speech Generation with Discrete Tokens
by: Shen, Feiyu, et al.
Published: (2023)
by: Shen, Feiyu, et al.
Published: (2023)
Token Pruning in Audio Transformers: Optimizing Performance and Decoding Patch Importance
by: Lee, Taehan, et al.
Published: (2025)
by: Lee, Taehan, et al.
Published: (2025)
PoolingVQ: A VQVAE Variant for Reducing Audio Redundancy and Boosting Multi-Modal Fusion in Music Emotion Analysis
by: Zou, Dinghao, et al.
Published: (2025)
by: Zou, Dinghao, et al.
Published: (2025)
Similar Items
-
Why Pre-trained Models Fail: Feature Entanglement in Multi-modal Depression Detection
by: Zhang, Xiangyu, et al.
Published: (2025) -
Zero-Shot Cognitive Impairment Detection from Speech Using AudioLLM
by: Shahin, Mostafa, et al.
Published: (2025) -
Beyond Video-to-SFX: Video to Audio Synthesis with Environmentally Aware Speech
by: Niu, Xinlei, et al.
Published: (2025) -
Mamba in Speech: Towards an Alternative to Self-Attention
by: Zhang, Xiangyu, et al.
Published: (2024) -
When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection
by: Zhang, Xiangyu, et al.
Published: (2024)