Imagen de Portada

From Hallucination to Articulation: Language Model-Driven Losses for Ultra Low-Bitrate Neural Speech Coding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yi, Jayeon, Kim, Minje
Formato:	Preprint
Publicado:	2026
Materias:	Audio and Speech Processing
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SPG-Codec: Exploring the Role and Boundaries of Semantic Priors in Ultra-Low-Bitrate Neural Speech Coding
por: Zhao, Mingyu, et al.
Publicado: (2026)

Entropy-Guided GRVQ for Ultra-Low Bitrate Neural Speech Codec
por: Ren, Yanzhou, et al.
Publicado: (2026)

Ultra-Low-Bitrate Mel-Spectrogram-based Neural Speech Coding with Flow-Matching-based Refinement and Vocoding-driven Reconstruction
por: Du, Hui-Peng, et al.
Publicado: (2026)

Multimodal Representation Loss Between Timed Text and Audio for Regularized Speech Separation
por: Hsieh, Tsun-An, et al.
Publicado: (2024)

Neural Speech and Audio Coding: Modern AI Technology Meets Traditional Codecs
por: Kim, Minje, et al.
Publicado: (2024)

CodeSep: Low-Bitrate Codec-Driven Speech Separation with Base-Token Disentanglement and Auxiliary-Token Serial Prediction
por: Du, Hui-Peng, et al.
Publicado: (2026)

Towards Bitrate-Efficient and Noise-Robust Speech Coding with Variable Bitrate RVQ
por: Chae, Yunkee, et al.
Publicado: (2025)

BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec
por: Xin, Detai, et al.
Publicado: (2024)

VoCodec: An Efficient Lightweight Low-Bitrate Speech Codec
por: Yang, Leyan, et al.
Publicado: (2026)

Hyperbolic Distance-Based Speech Separation
por: Petermann, Darius, et al.
Publicado: (2024)

Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer
por: Shechtman, Slava, et al.
Publicado: (2024)

Neural Speech Coding for Real-time Communications using Constant Bitrate Scalar Quantization
por: Brendel, Andreas, et al.
Publicado: (2024)

Personalized Neural Speech Codec
por: Jang, Inseon, et al.
Publicado: (2024)

Optimizing Neural Speech Codec for Low-Bitrate Compression via Multi-Scale Encoding
por: Yang, Peiji, et al.
Publicado: (2024)

MuCodec: Ultra Low-Bitrate Music Codec
por: Xu, Yaoxun, et al.
Publicado: (2024)

DDD: A Perceptually Superior Low-Response-Time DNN-based Declipper
por: Yi, Jayeon, et al.
Publicado: (2024)

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

Perceptual Audio Coding: A 40-Year Historical Perspective
por: Herre, Jürgen, et al.
Publicado: (2025)

TGIF: Talker Group-Informed Familiarization of Target Speaker Extraction
por: Hsieh, Tsun-An, et al.
Publicado: (2025)

Adaptive Deterministic Flow Matching for Target Speaker Extraction
por: Hsieh, Tsun-An, et al.
Publicado: (2025)

Scaling Transformers for Low-Bitrate High-Quality Speech Coding
por: Parker, Julian D, et al.
Publicado: (2024)

MSR-Codec: A Low-Bitrate Multi-Stream Residual Codec for High-Fidelity Speech Generation with Information Disentanglement
por: Li, Jingyu, et al.
Publicado: (2025)

Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations
por: Jiang, Xue, et al.
Publicado: (2025)

LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec
por: Guo, Yiwei, et al.
Publicado: (2024)

A Comparative Analysis of Poetry Reading Audio: Singing, Narrating, or Somewhere In Between?
por: Choi, Kahyun, et al.
Publicado: (2024)

Creating Personalized Synthetic Voices from Articulation Impaired Speech Using Augmented Reconstruction Loss
por: Tian, Yusheng, et al.
Publicado: (2024)

FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks
por: Della Libera, Luca, et al.
Publicado: (2025)

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

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

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

XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs
por: Gong, Yitian, et al.
Publicado: (2025)

FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation
por: Della Libera, Luca, et al.
Publicado: (2025)

Combolutional Neural Networks
por: Churchwell, Cameron, et al.
Publicado: (2025)

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

SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound
por: Liu, Haohe, et al.
Publicado: (2024)

Speech Separation using Neural Audio Codecs with Embedding Loss
por: Yip, Jia Qi, et al.
Publicado: (2024)

Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers
por: Lin, Jackie, et al.
Publicado: (2026)

Aligning Speech to Languages to Enhance Code-switching Speech Recognition
por: Liu, Hexin, et al.
Publicado: (2024)

Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine
por: Kuznetsova, Anastasia, et al.
Publicado: (2025)

MDCTCodec: A Lightweight MDCT-based Neural Audio Codec towards High Sampling Rate and Low Bitrate Scenarios
por: Jiang, Xiao-Hang, et al.
Publicado: (2024)