X-Translator is a low-cost modular system for real-time speech-to-speech translation, using streaming ASR, machine translation, and prompt-conditioned TTS, with session-level control.

The paper introduces OpenSTBench, a unified, multidimensional evaluation framework designed to comprehensively compare heterogeneous speech translation systems by jointly assessing translation, speech…

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 DOA, a training-free attention policy that leverages self-attention in decoder-only SpeechLLMs to achieve high-quality, low-latency simultaneous long-form translation without requir…

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

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

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…

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 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.

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 proposes ESRT, an edge-cloud framework that achieves state-of-the-art, bandwidth-efficient, and privacy-preserving many-to-many speech translation across 45 languages by splitting the model…

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.

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,…

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 presents the tttAI system for time-stamped speaker-attributed speech recognition in smart-glasses recordings, achieving a tcpCER of 7.10% on Track 1 and 34.04% on Track 2.