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 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.

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…

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…

This paper investigates the ability of mean opinion score (MOS) prediction models to capture quality differences in text-to-speech beyond acoustic fidelity through controlled perturbations on speech.

The authors present ZONOS2 8B, a TTS model with improved naturalness, prosody, and voice cloning fidelity, achieved through scaling, data expansion, and simplification.

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

The paper proposes RTFree-F5, a method to make flow-matching TTS models like F5-TTS independent of reference transcripts, improving performance and naturalness for dysarthric speakers.

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

This paper investigates the effectiveness of incorporating synthetic speech data in Automatic Speech Recognition (ASR) Systems for three Indic languages by analyzing performance gains, script sources,…

The paper describes a method to optimize the style vector for text-to-speech systems without a reference encoder, improving similarity and acceptance rate.

Chatterbox-Flash introduces a prior-calibrated block diffusion model for zero-shot TTS that achieves high-fidelity, streaming synthesis with significantly lower computational overhead than existing me…

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

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…

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