Cover Image

MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yeh, Sung-Lin, Zhou, Wei, Keren, Gil, Le, Duc, Meng, Zhong, Tang, Hao, Mahadeokar, Jay, Kalinli, Ozlem, Mourachko, Alexandre
Format:	Preprint
Published:	2026
Subjects:	Audio and Speech Processing Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Faster Speech-LLaMA Inference with Multi-token Prediction
by: Raj, Desh, et al.
Published: (2024)

CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR
by: Zhou, Wei, et al.
Published: (2024)

Efficient Streaming LLM for Speech Recognition
by: Jia, Junteng, et al.
Published: (2024)

M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses
by: Yang, Yufeng, et al.
Published: (2024)

Token-Weighted RNN-T for Learning from Flawed Data
by: Keren, Gil, et al.
Published: (2024)

Mel-FullSubNet: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR
by: Zhou, Rui, et al.
Published: (2024)

Estimating the Completeness of Discrete Speech Units
by: Yeh, Sung-Lin, et al.
Published: (2024)

CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR
by: Shao, Nian, et al.
Published: (2025)

Is GAN Necessary for Mel-Spectrogram-based Neural Vocoder?
by: Du, Hui-Peng, et al.
Published: (2025)

Can Speech LLMs Think while Listening?
by: Shih, Yi-Jen, et al.
Published: (2025)

A Mel Spectrogram Enhancement Paradigm Based on CWT in Speech Synthesis
by: Hu, Guoqiang, et al.
Published: (2024)

Music Genre Classification: A Comparative Analysis of CNN and XGBoost Approaches with Mel-frequency cepstral coefficients and Mel Spectrograms
by: Meng, Yigang
Published: (2024)

Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech
by: Kang, Wonjune, et al.
Published: (2024)

DMF2Mel: A Dynamic Multiscale Fusion Network for EEG-Driven Mel Spectrogram Reconstruction
by: Fan, Cunhang, et al.
Published: (2025)

Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation
by: Guo, Hongming, et al.
Published: (2024)

Mel-Spectrogram Inversion via Alternating Direction Method of Multipliers
by: Masuyama, Yoshiki, et al.
Published: (2025)

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

ESTVocoder: An Excitation-Spectral-Transformed Neural Vocoder Conditioned on Mel Spectrogram
by: Jiang, Xiao-Hang, et al.
Published: (2024)

SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG
by: Fan, Cunhang, et al.
Published: (2025)

Conversational Speech Naturalness Predictor
by: Xu, Anfeng, et al.
Published: (2026)

Learning Speech Representations with Variational Predictive Coding
by: Yeh, Sung-Lin, et al.
Published: (2025)

Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuning
by: Ma, Yingyi, et al.
Published: (2024)

Effective internal language model training and fusion for factorized transducer model
by: Guo, Jinxi, et al.
Published: (2024)

Whisper Has an Internal Word Aligner
by: Yeh, Sung-Lin, et al.
Published: (2025)

Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition
by: Deng, Keqi, et al.
Published: (2024)

A Neural Denoising Vocoder for Clean Waveform Generation from Noisy Mel-Spectrogram based on Amplitude and Phase Predictions
by: Du, Hui-Peng, et al.
Published: (2024)

Mel-McNet: A Mel-Scale Framework for Online Multichannel Speech Enhancement
by: Yang, Yujie, et al.
Published: (2025)

Fusion of Modulation Spectrogram and SSL with Multi-head Attention for Fake Speech Detection
by: N, Rishith Sadashiv T, et al.
Published: (2025)

Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model
by: Xie, Jiamin, et al.
Published: (2023)

Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolution
by: Yu, Chin-Yun, et al.
Published: (2022)

Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs
by: Langman, Ryan, et al.
Published: (2024)

MelHuBERT: A simplified HuBERT on Mel spectrograms
by: Lin, Tzu-Quan, et al.
Published: (2022)

Hierarchical Decoding for Discrete Speech Synthesis with Multi-Resolution Spoof Detection
by: Zhao, Junchuan, et al.
Published: (2026)

Latent Filling: Latent Space Data Augmentation for Zero-shot Speech Synthesis
by: Bae, Jae-Sung, et al.
Published: (2023)

A Survey of Deep Learning for Complex Speech Spectrograms
by: Xie, Yuying, et al.
Published: (2025)

Improving Streaming Speech Recognition With Time-Shifted Contextual Attention And Dynamic Right Context Masking
by: Le, Khanh, et al.
Published: (2025)

Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy
by: Xue, Ke, et al.
Published: (2026)

SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation
by: Fucci, Dennis, et al.
Published: (2024)

Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens
by: Zhao, Jinzheng, et al.
Published: (2024)

dMel: Speech Tokenization made Simple
by: Bai, Richard He, et al.
Published: (2024)