Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2605.29859

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

Sung-Lin Yeh·Wei Zhou·Gil Keren·Duc Le·Zhong Meng·Hao Tang·Jay Mahadeokar·Ozlem Kalinli·Alexandre Mourachko
View original source ↗Read source document ↗Export metadata ↓

Abstract

Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downstream objectives, the extracted representations may not be optimal for downstream tasks. To address this limitation, we introduce a discrete latent variable model on mel spectrograms that jointly optimizes the encoder and the speech language model. Joint optimization not only brings improvements over codec-based and other mel-spectrogram-based baselines on zero-shot Text-to-Speech (TTS) and Speech-to-Text (STT) tasks, but also effectively alleviates common issues in autoregressive mel spectrogram modeling, such as prolonged silence generation and word omissions.

Explore related subjects

eess.AScs.CL

Keep this discovery

BibTeXRIS

Sung-Lin Yeh, Wei Zhou, Gil Keren, Duc Le, Zhong Meng, Hao Tang, Jay Mahadeokar, Ozlem Kalinli, Alexandre Mourachko. 2026-09-01. MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables. https://arxiv.org/abs/2605.29859

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

cs.CL subjecteess.AS subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related papers

arXiv2026

Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition

Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G), enabling cross-lingual acoustic sharing while keeping language-specific orthography in a separate module. While large language models (LLMs) are promising for P2G, multilingual P2G remains challenging due to language-aware generation and severe cross-language data imbalance. We study multilingual LLM-based P2G on the ten-language CV-Lang10 benchmark. We examine robustness strategies that account for S2P uncertainty, including DANP and Simplified SKM (S-SKM). S-SKM is a Monte Carlo approximation that avoids CTC-based S2P probability weighting in P2G training. Robust training and low-resource oversampling reduce the average WER from 10.56% to 7.66%.

eess.AS↗
arXiv2026

Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of different features to model representations cannot be directly compared, and feature correlations can affect probing results. We present an Encoding Probe that reverses this direction and reconstructs internal representations of models using interpretable features. We evaluate this method on text and speech transformer models, using feature sets spanning acoustics, phonetics, syntax, lexicon, and speaker identity. Our results suggest that speaker-related effects vary strongly across different training objectives and datasets, while syntactic and lexical features contribute independently to reconstruction. These results show that the Encoding Probe provides a complementary perspective on interpreting model representations beyond decodability.

cs.CL↗
arXiv2026

Automatic Speech Recognition for Multilingual Oral History Research

This paper offers a unique perspective on how speech technologies are being adopted by community-led heritage language preservation and revitalisation initiatives. As a community-led language maintenance strategy, oral histories play a crucial role in Cantonese language revitalisation in New Zealand. The development of Automatic Speech Recognition (ASR) toolkits, such as Whisper, have expedited what has often been a resource and time-intensive process of transcribing oral history collections. However, there is limited research into the effectiveness of ASR toolkits when applied to code-switched language contexts. Based on Word Error Rate (WER), the best performing Whisper model configuration achieved a WER of 12.10 at the expense of accurately transcribing unsupported non-English segments. However, Whisper remains a useful tool by providing a first-pass transcription using only 1% of the estimated time otherwise needed for manual transcription.

eess.AS↗