The paper introduces SCIC, a method that enhances speaker‑adapted expressive TTS by conditioning prosody instructions on both scope and codebook usage. SCIC uses a Temporal Instruction Router to activate frame‑level tags and Tag‑Specific Codebook Weighting to target residual codebooks for Pitch, Energy, and Speed, while Pause uses absolute durations. The approach improves clause‑level prosodic control and yields a clearer paragraph‑level expressive hierarchy compared to standard instruction fine‑tuning, with post‑training optimization preserving quality and speaker similarity.
arXiv:2608.28970v1 Announce Type: cross Abstract: Current TTS systems typically rely on open-loop, single-pass generation and can produce sporadic local prosodic defects, such as misplaced stress, un...
TontaubeV1 is a streaming text‑to‑speech model that preserves natural prosody while running on a single consumer GPU. It encodes speech with a hierarchical DualCodec representation at 12.5 Hz, separating a semantic stream from successive acoustic refinements, and uses Qwen3‑derived transformers to predict the semantic stream, utterance duration, and acoustic refinements. The system supports up to one minute of reference audio for voice conditioning, streams with a 200 ms latency to first audio, and achieves real‑time factors of 0.08 (single input) and 0.02 (eight concurrent inputs).
arXiv:2606. 07547v1 Announce Type: cross Abstract: Speech-based large language models are typically constrained to spoken replies, which limits their user-facing outputs to what can be verbalized and suppresses text-native capabilities such as code generation, structured analysis, and multi-step reasoning in realtime interaction, for tasks that require persistent, structured, and inspectable intermediate outputs.
StyleStream 2.0 is a fast, controllable streaming voice style conversion system that reduces end‑to‑end latency to about 520 ms on a consumer GPU, halving the delay of its predecessor while preserving conversion quality. It replaces mel‑spectrogram context with a compact style embedding, enabling a unified text‑conditioned flow model that supports both text‑based voice design and instruction‑based voice editing. Experiments demonstrate that StyleStream 2.0 achieves superior target style fidelity, voice design, and voice editing performance while maintaining intelligibility and attribute preservation.
TontaubeV1 is a streaming text‑to‑speech model that maintains natural prosody while running on a single consumer GPU. It encodes speech with a hierarchical DualCodec representation at 12.5 Hz, separating a semantic stream from successive acoustic refinements, and uses Qwen3‑derived transformers to predict the semantic stream and add refinements. The model supports up to one minute of reference audio for voice conditioning, streams with a 200 ms latency to first audio, and achieves real‑time factors of 0.08 (single input) and 0.02 (eight concurrent inputs).
arXiv:2608. 02673v1 Announce Type: cross Abstract: Speech editing for content creation requires precise control over both what an edit should do and where it should apply.
arXiv:2608. 08638v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools.
X-VC is a zero‑shot streaming voice conversion system that performs one‑step conversion directly in the latent space of a pretrained neural codec. It employs a dual‑conditioning acoustic converter that jointly models source codec latents and target acoustic conditions, while using adaptive normalization to inject utterance‑level speaker information. The model is trained with generated paired data and a role‑assignment strategy, and uses a chunkwise inference scheme with overlap smoothing to achieve low‑latency streaming inference, achieving superior WER, speaker similarity, and real‑time factor on the Seed‑TTS‑Eval benchmark.
arXiv:2606. 01802v1 Announce Type: cross Abstract: MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning.
GEPARD is a streaming text‑to‑speech model that uses a standard large language model backbone to generate speech autoregressively, decoding audio with an FSQ‑based neural codec. It streams audio chunk‑by‑chunk as text arrives, achieving a real‑time factor of about 0.067 and an aggregate speedup of roughly 204× on a single GPU with 256 concurrent streams. The design keeps all complex auxiliary mechanisms outside the decode loop, enabling deployment with a standard LLM engine (vLLM) without kernel modifications.
arXiv:2608. 11590v1 Announce Type: cross Abstract: Human voice generation has made rapid progress in speech generation, singing voice generation, voice cloning, and voice editing.
X2Streaming-ASR introduces a method for streaming automatic speech recognition that separates the decision of when to commit a transcript from what to commit. The approach uses a three‑stage training process: first establishing streaming capability, then warm‑starting a commit policy with automatically probed trajectories, and finally refining the policy with character‑level, segment‑assigned group‑relative rewards for accuracy and latency. On AISHELL‑1/2/3 and WenetSpeech datasets, the system achieves mean character‑level commit latencies of 27–84 ms, far lower than baseline systems, while also attaining the best streaming character error rates on AISHELL‑1 and AISHELL‑3.