Cover Image

Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zheng, Rong, Xiaobin, Su, Hang, Tan, Tianyi, Wu, Junnan, Fan, Lichun, Luo, Zhenbo, Luan, Jian, Lu, Jing
Format:	Preprint
Published:	2026
Subjects:	Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement
by: Rong, Xiaobin, et al.
Published: (2025)

Thinking in cocktail party: Chain-of-Thought and reinforcement learning for target speaker automatic speech recognition
by: Zhang, Yiru, et al.
Published: (2025)

Lightweight speech enhancement guided target speech extraction in noisy multi-speaker scenarios
by: Huang, Ziling, et al.
Published: (2025)

StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement
by: Rong, Xiaobin, et al.
Published: (2026)

UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations
by: Rong, Xiaobin, et al.
Published: (2026)

Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding
by: Shao, Mingchen, et al.
Published: (2026)

GAP-URGENet: A Generative-Predictive Fusion Framework for Universal Speech Enhancement
by: Rong, Xiaobin, et al.
Published: (2026)

Adaptive Convolution for CNN-based Speech Enhancement Models
by: Wang, Dahan, et al.
Published: (2025)

A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions
by: Wang, Zheng, et al.
Published: (2025)

LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization
by: Jo, Daejin, et al.
Published: (2025)

UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search
by: Rong, Xiaobin, et al.
Published: (2025)

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network
by: Rong, Xiaobin, et al.
Published: (2025)

Dynamic Frequency-Adaptive Knowledge Distillation for Speech Enhancement
by: Yuan, Xihao, et al.
Published: (2025)

Assessing the Impact of Noise and Speech Enhancement on the Intelligibility of Speech Codecs
by: Behringer, Lyonel, et al.
Published: (2026)

Flexible Multichannel Speech Enhancement for Noise-Robust Frontend
by: Jukić, Ante, et al.
Published: (2024)

Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation
by: Hwang, Min-Jae, et al.
Published: (2024)

Hallucination in Perceptual Metric-Driven Speech Enhancement Networks
by: Close, George, et al.
Published: (2024)

Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio question answering
by: Zhao, Jinghua, et al.
Published: (2025)

Improving Design of Input Condition Invariant Speech Enhancement
by: Zhang, Wangyou, et al.
Published: (2024)

Linguistic Knowledge Transfer Learning for Speech Enhancement
by: Hung, Kuo-Hsuan, et al.
Published: (2025)

Reasoning Beyond Majority Vote: An Explainable SpeechLM Framework for Speech Emotion Recognition
by: Su, Bo-Hao, et al.
Published: (2025)

Electrolaryngeal Speech Intelligibility Enhancement Through Robust Linguistic Encoders
by: Violeta, Lester Phillip, et al.
Published: (2023)

Investigation of Speech and Noise Latent Representations in Single-channel VAE-based Speech Enhancement
by: Li, Jiatong, et al.
Published: (2025)

DISPATCH: Distilling Selective Patches for Speech Enhancement
by: Kim, Dohwan, et al.
Published: (2025)

Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders
by: Sun, Xingwei, et al.
Published: (2025)

Test-Time Adaptation for Speech Enhancement via Domain Invariant Embedding Transformation
by: Raichle, Tobias, et al.
Published: (2025)

DiffVQE: Hybrid Diffusion Voice Quality Enhancement Under Acoustic Echo and Noise
by: Girao, Haljan Lugo, et al.
Published: (2026)

CFMDCTCodec: A Low-Bitrate Neural Speech Codec with Noise-Prior-aware Conditional Flow Matching for MDCT-Spectral Enhancement
by: Jiang, Xiao-Hang, et al.
Published: (2026)

Tracking Listener Attention: Gaze-Guided Audio-Visual Speech Enhancement Framework
by: Yang, Hsiang-Cheng, et al.
Published: (2026)

Hybrid Real- And Complex-Valued Neural Network Concept For Low-Complexity Phase-Aware Speech Enhancement
by: Fiorio, Luan Vinícius, et al.
Published: (2025)

Leveraging Local and Global Knowledge Integration with Time-Frequency Calibrated Distillation for Speech Enhancement
by: Cheng, Jiaming, et al.
Published: (2025)

Robust One-step Speech Enhancement via Consistency Distillation
by: Xu, Liang, et al.
Published: (2025)

Complex Recurrent Variational Autoencoder with Application to Speech Enhancement
by: Xie, Yuying, et al.
Published: (2022)

SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement
by: Li, Xingchen, et al.
Published: (2025)

Borderless Long Speech Synthesis
by: Song, Xingchen, et al.
Published: (2026)

Autoregressive Speech Enhancement via Acoustic Tokens
by: Della Libera, Luca, et al.
Published: (2025)

Diffusion-based Speech Enhancement with Schrödinger Bridge and Symmetric Noise Schedule
by: Wang, Siyi, et al.
Published: (2024)

Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection
by: Fan, Cunhang, et al.
Published: (2023)

SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization
by: Chen, Wenxi, et al.
Published: (2025)

Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation
by: Matsuura, Kohei, et al.
Published: (2024)