arXiv:2407.15828v2 Announce Type: replace
Abstract: Spoken dialogue is essential for human-AI interactions, providing expressive capabilities beyond text. Developing effective spoken dialogue systems (SDSs) requires large-scale, high-quality, and dive…
arXiv:2604.02043v1 Announce Type: new
Abstract: Self-supervised speech models learn effective representations of spoken language, which have been shown to reflect various aspects of linguistic structure. But when does such structure emerge in model tr…
arXiv:2604.00688v2 Announce Type: replace
Abstract: We present OmniVoice, a massive multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is a novel diffusion language model-style discrete non-autoregressive …
arXiv:2604.02102v1 Announce Type: new
Abstract: Speech representations from self-supervised speech models (S3Ms) are known to be sensitive to phonemic contrasts, but their sensitivity to prosodic contrasts has not been directly measured. The ABX discr…
arXiv:2604.00688v1 Announce Type: new
Abstract: We present OmniVoice, a massive multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is a novel diffusion language model-style discrete non-autoregressive (NAR…
arXiv:2508.15860v3 Announce Type: replace-cross
Abstract: Finite Scalar Quantization (FSQ) offers simplified training but suffers from residual magnitude decay in multi-stage settings, where subsequent stages receive exponentially weaker signals. We p…
arXiv:2603.29042v1 Announce Type: cross
Abstract: Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive. Highly performant English-focused models do not generalize acro…
arXiv:2601.13802v2 Announce Type: replace
Abstract: Arabic spans over 30 spoken varieties, yet no open-source text-to-speech system unifies them. Key barriers include substantial cross-dialect lexical and phonological divergence, scarce synthesis-grad…
arXiv:2603.29217v1 Announce Type: cross
Abstract: Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G), enabling cross-lingual acoustic sharing while keeping language-specific orthography in a separate mo…
arXiv:2511.06458v2 Announce Type: replace-cross
Abstract: Acoustic Environment Matching (AEM) is the task of transferring clean audio into a target acoustic environment, enabling engaging applications such as audio dubbing and auditory immersive virtu…