The paper introduces PlanAudio, a unified LLM-based framework that directly synthesizes natural, composite audio containing speech and sounds from unconstrained free-form text prompts, outperforming e…

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 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…

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 proposes methods for generating global prosodic embeddings using auto-encoder models of pitch and energy, demonstrating competitive or superior performance under challenging conditions.

Eight voice cloning models are benchmarked on five paralinguistic tasks, showing most preserve signal with modest degradation. Cloning English clinical speech into Japanese outperforms raw cross-lingu…

The paper introduces the Designed Vocalizations Dataset for AI-based voice conversion research on non-human vocalizations and effects, providing a standardized test set and benchmark results.

The paper introduces StreamSynth, a sequential setting for synthetic data generation, and proposes SynLearner, a framework that enables LLMs to improve synthesis performance by accumulating and transf…

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

MindVoice is a neuro-to-speech framework that uses pretrained priors to disentangle and reconstruct intelligible speech from noisy, non-invasive neural signals, significantly outperforming existing me…

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

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