Acoustic capture, device processing, and transmission coding in real calls jointly alter speech signals and may affect the reliability of audio deepfake detection. To systematically evaluate these effects, we introduce RealComm, a dataset pairing digital speech with recordings of the same utterances transmitted through...
Li Wang, Jin-Dong Wang, Wan Lin et al.· 0 citations
We present AnyEdit, a unified, separation-free framework for speech and singing voice editing that preserves real-world acoustic environments, including noise, reverberation, and background music. Recent unified generative models already achieve strong speech and singing generation in clean conditions, but real-world v...
Yun-Jia Zhang, Ju-Nan Zhang, Jing Yang et al.· 0 citations
Chunk-interleaved full-duplex speech language models listen and speak in fixed time chunks, and each chunk must be processed before the next one arrives. Their workload is asymmetric across chunks: listen chunks leave compute idle while awaiting audio, and speak and tool-call chunks require serial generation, which del...
Yu-Tong Bian, Yang-Lin Zhang, Yu-Xiang Wang et al.· 0 citations
ReListen is a training-free method in which a frozen audio language model finds its own evidence before answering, and its memory stays constant even for recordings too long to hear whole on one GPU, therefore, a frozen audio language model can search hour-long recordings by itself, without a transcript or additional t...
Ming-Hao Hsu, Shu-Jie Liu, Yuxuan Hu et al.· 0 citations
Interactive models increasingly hand complex reasoning and tool use to a slow brain in the background, leaving a realtime front model free to sustain full-duplex dialogue. Yet the user may refine, cancel or replace a request while its task runs, so a plan or result that made sense a moment ago goes stale. Each new utte...
Yu-Xiang Wang, Sheng-Bo Cai, Zhi-Xian Zhao et al.· 0 citations
Instruction-controlled speech synthesis and paralinguistic understanding are often trained independently, leaving reciprocal feedback between the two tasks underexplored. We introduce CycleSpeech, a framework that connects generation and understanding through a shared, structured voice profile that serves as a common t...
Huan Liao, Hao-Nan Han, Xing-Wen Han et al.· 0 citations
Speech and audio language models connect continuous acoustic representations to decoders pretrained primarily on text data. Most such models use MLP or Q-Former interfaces to map acoustic features into the decoder's input space, requiring the decoder to learn how to interpret the resulting representations. We investiga...
Ming-Hao Hsu, Shu-Jie Liu, Yuxuan Hu et al.· 1 citation
Affine Fields for Interface Repair across Modalities (AFFIRM) is introduced, which first learns and freezes a base correction for speech hidden states, then adds query-specific corrections with zero mean over the operator-training queries.
Ming-Hao Hsu, Yu-Xiang Wang, Ying Shen et al.· 1 citation
Generative speech enhancement models can produce cleaner and more natural-sounding speech than conventional discriminative approaches, but may hallucinate by changing speech content or speaker identity, even with transcript conditioning. We present AuraSE, a flow-matching framework that addresses hallucination through...
Ying Shen, Yao Qian, Yuxuan Hu et al.· 0 citations
Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, while search, reasoning, and coding are handled through asynchronous delegation. A duplex model supports continuous listening and speaking, but complex reasoning and tool u...
Ying Shen, Yu-Xiang Wang, Kun-Yu Feng et al.· 0 citations
Modern text-to-speech (TTS) systems are rarely deployed as unchanged pre-trained models. They are often adapted through supervised fine-tuning (SFT) or preference optimization such as DPO and GRPO. This raises a practical question for audio deepfake forensics: do fingerprints learned from a foundation generator remain...
Li Wang, Kun-Yu Feng, Wan Lin et al.· arXiv.org· 0 citations
AURAL is introduced, which models a distribution over multiple plausible reasoning continuations in latent space and jointly predicts chunks of future states to reduce sequential forward passes and reasoning latency and shows that harder questions elicit more latent reasoning steps.
Yu-Xiang Wang, Kun-Yu Feng, Yuan-Cheng Wang et al.· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.