This paper analyzes speech-text interleaved language models and reveals that they go through an implicit transcription phase in which spoken words become decodable as text in intermediate layers.

The paper introduces three new Korean speech benchmarks (KVoiceBench, KOpenAudioBench, and KMMAU) to evaluate SpeechLMs, demonstrating that English-centric evaluation fails to capture performance gaps…

PolySpeech-100 introduces a massive, multi-lingual benchmark covering 110 linguistic variants to rigorously test Speech-LLMs, demonstrating that open-source models struggle with low-resource languages…

The paper proposes SpeechKV, a method to compress speech sequences inside large language models using a learned pooling, maintaining performance and delivering decoding speedup.

The paper introduces SPEARBench, a benchmark for evaluating naturalness in speech-to-speech language models using a multidimensional protocol.

CORTIS is a text-only adaptation framework that fine-tunes spoken language models for task-oriented voice agents using text-form task supervision.

The paper proposes LaSR, a context-aware training paradigm that uses latent reasoning to significantly improve speech recognition, especially for specialized terminology, without adding latency.

SALSA is a lightweight adaptation method that learns layer-wise steering vectors to significantly improve the performance of speech-aware LLMs on out-of-domain speech tasks.

HoliTok introduces a novel continuous holistic tokenization model that provides a unified, high-fidelity latent representation for simultaneously supporting both speech generation and speech understan…

MEUSLI introduces an open-source multilingual projector family linking a Whisper encoder with LLMs, enabling end-to-end ASR in 28 European languages and supporting multilingual speech translation and…

The paper introduces SURE, a unified framework designed to standardize and improve the comparability and reproducibility of evaluations for advanced speech understanding models.

This paper investigates the relationship between language model perplexity and word error rate in modern automatic speech recognition systems, studying the impact of external language models, encoder…

This paper investigates the use of various acoustic features for recognizing dysarthric speech using a Factorized Time Delay Neural Network (F-TDNN) model, achieving a relative improvement of 4.65% in…

The paper introduces GigaSpeechBench, a comprehensive multilingual and multidimensional ASR & AST benchmark with 680 hours of human-annotated speech, featuring 12 low-resource languages, 6 Chinese dia…

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.

The paper introduces Dialogs, a new Russian conversational speech corpus with high-quality recordings, segmented utterances, and expressive prosody labels.

The paper argues that large language models (LLMs) are a special case of world models and proposes a continuous spectrum between token prediction and latent-space architectures.

This paper explores the effect of conversational timing properties on automatic speech recognition (ASR) systems by controlling and optimizing pause and overlap timing distributions.