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 proposes Joint Speech-Text Interleaved Pretraining (JSTIP) for speech recognition, which constructs interleaved speech-text sequences and achieves consistent entity accuracy improvement.

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 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.

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…

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 presents a method for building a compact Hindi text-to-speech model by pruning a large teacher model under a severe data budget, achieving state-of-the-art performance.

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

The paper introduces BEA-Dialogue+, an expanded 200-hour corpus for Hungarian conversational ASR, demonstrating that while larger data is challenging, specialized fine-tuning techniques significantly…

A lightweight framework for automated pronunciation assessment using native speech resources and unsupervised or lightly calibrated methods.

This paper introduces a training recipe for sentence-level and long-form streaming speech-to-speech translation using only 2k hours of paired cross-lingual data and auxiliary supervision.

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…

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

Murmur is an efficient inference system for long-form ASR that resolves the accuracy-latency trade-off by optimizing both inter-chunk processing and intra-chunk attention mechanisms.

This paper introduces StellarTTS, a mobile-optimized non-autoregressive text-to-speech framework with sparse temporal embeddings and a semantic-aware codec, achieving lower latency and stronger robust…

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.

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…