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…

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 fine-tunes two zero-shot text-to-speech models, Chatterbox and CosyVoice 3, on Singlish speakers from the IMDA National Speech Corpus to improve accent similarity and naturalness.

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

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…

ImmersiveTTS is an environment-aware text-to-speech model that generates natural speech seamlessly integrated within environmental contexts by explicitly modeling cross-modal interactions, achieving s…

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

This paper introduces Re-Sonance, a real-time speech-driven AAC system for professional speaking scenarios using LLM-enhanced Whisper ASR, Qwen LLM, and CosyVoice TTS.

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

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.

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

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

This paper introduces the REAL-TSE Challenge, a satellite challenge on target speaker extraction from real conversational recordings, and describes its task definition, datasets, evaluation protocol,…

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…