Real-Time Avatars, Latent Reasoning, and Physically Grounded Speech

3D Gaussian avatars support fast rendering, however, their real-time animation is often challenged by the costly neural inference. We address this bottleneck and show that the animation of pretrained avatar models can be closely approximated by a linear combination of identity-independent blendshapes. Building on this finding, we introduce GALA (Gaussian Animation via Linear Approximation), a distillation method that replaces per-frame heavy neural decoding with a shallow coefficient predictor and a linear blend. To improve fidelity and reduce memory requirements, we propose to construct the basis using block-local PCA under a rendering-aware metric and a memory budget. Our method learns a shallow MLP network to predict blendshape coefficients and applies to various animation architectures without retraining original models. We validate GALA by accelerating the inference of three distinct avatar models for 3D animation of facial expressions and full-bodies with clothing dynamics. Across these models, our distillation generalizes to held-out identities and reduces CPU animation cost by up to three orders of magnitude while preserving most of the rendering quality. Excellent results of our method confirm the shared linear structure of learned avatar representations and enable highly efficient and accurate animation at frame rates reaching up to 60fps on mobile devices. Project page: https://ramazan793.github.io/gala/

Dubbing quality control requires a reference-free judge that can determine whether a candidate text line matches a speaker's visible articulation in both content and timing, using only silent video and text because dubbed audio may not yet exist. Existing visual speech recognizers and video-language models are poorly suited to this setting: even when fine-tuned to recover spoken content from lip motion, they remain largely insensitive to temporal errors. We introduce $\textit{Align Then Reason}$ (ATR), a multilingual lip-sync judge that first establishes a monotonic alignment between frame-level lip representations and the phonetic units of the candidate line, then reasons over this alignment to make the final judgment. An alignment scorer provides the LLM with both local evidence for each phonetic unit and a calibrated global alignment score, enabling it to reason jointly about content and timing. On a seven-language benchmark, our method improves mean AUC over the corresponding Qwen3.5 SFT baselines by 59.4%, 50.2%, and 50.8% with 2B, 4B, and 9B reasoners, respectively. The gains generalize across LLM families, reaching mean AUC improvements of 45.9% and 46.6% over the best baseline for LLaMA-3.1-8B and Mistral-7B, respectively. They also transfer across datasets to three unseen MuAViC languages. Furthermore, we evaluate on two downstream tasks built from real dubbing lines. On dub-line reranking, ATR-9B outperforms the best lip-reading baseline by 52.0%, while on script-to-clip assignment, ATR-9B improves over the best lip-reading baseline by 17.7%.

Video-to-speech synthesis aims to generate natural-sounding speech from silent talking-face videos while ensuring phonetic accuracy. A fundamental challenge in this task is the inherent one-to-many mapping problem, where visual dynamics often lack sufficient information to uniquely determine the corresponding utterance. To address this, we propose Watch Your Speech (WYS), a video-to-speech synthesis framework that incorporates textual conditioning as an explicit linguistic cue to mitigate visual ambiguity. Our framework features an attention-based embedding fusion module that synergistically integrates textual context with video sequences, coupled with a conditional flow matching objective for high-fidelity speech generation. Extensive experiments on the LRS2 and LRS3 datasets demonstrate that WYS achieves superior performance, establishing new state-of-the-art results in audio-visual synchronization (LSE-C/D) while maintaining highly competitive textual accuracy (WER). Subjective evaluations further confirm that our model generates speech with near-human naturalness, validating the effectiveness of textual conditioning in content-controlled video-to-speech synthesis. Project page: https://github.com/gunwoo5034/Watch-your-Speech

Model intelligence and fast response jointly shape the quality of interaction with speech language models, yet remain difficult to achieve together. Explicit chain-of-thought (CoT) improves reasoning and audio understanding, but generating intermediate reasoning tokens delays responses. Describing fine-grained acoustic cues further lengthens CoT and increases latency. Latent reasoning can reduce this overhead, yet existing methods often trail CoT and remain limited by single-path supervision and reasoning budgets that do not adapt to problem difficulty. We introduce AURAL, 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. To provide initial supervision for latent reasoning, we construct AuralReason-683K: 683K bilingual speech utterances (about 1,000 hours) with concise CoT for emotion recognition, empathetic dialogue, and general reasoning. AURAL-RL then explores beyond these traces, rewarding concise reasoning that yields high-quality answers and adapting reasoning effort to each problem. Across two backbones, AURAL-RL achieves performance comparable to CoT-RL, with larger gains over the respective supervised checkpoints on most metrics. Analysis further shows that harder questions elicit more latent reasoning steps. On Qwen2.5-Omni, it reduces time to the first answer token by 11.8x, from 1.22 to 0.10 s, versus 0.05 s for direct answering.

Voice agents enable low-latency, natural interaction, yet their ability to faithfully ground responses in external documents remains underexplored. We introduce DuplexSpeechBench-Document Grounding (DSB-DG), a benchmark for evaluating document grounding in voice agents across five professional domains. DSB-DG targets three failure modes: Context Saturation, which measures grounding under increasing document length; Grounding Decay, which measures retention of document facts across multi-turn dialogue; and Proactive Grounding, which evaluates whether context re-injection mitigates conversational drift. The benchmark contains 1,636 adversarially verified QA pairs from 50 documents covering five professional domains, and supports fully automatic evaluation of grounding accuracy, hallucination, and response latency. Across systems spanning cascaded, proprietary full-duplex and real-time, and open-weight speech2speech architectures, we find substantial differences in effective grounding capacity. While cascaded pipeline (ASR-LLM-TTS) achieves the highest grounding accuracy, Gemini-Live and GPT-Realtime closely trail behind. Open-weight systems exhibit distinct failure modes, most notably an abrupt context-capacity collapse and multi-turn grounding decay. More broadly, grounding fidelity degrades with context and conversational load, and failures frequently manifest as unsupported generations rather than abstention. We show that contextual grounding as a key unresolved challenge for reliable full-duplex voice agents.

Encoder-based speech large language models (Speech-LLMs) commonly employ pretrained speech encoders that prioritize linguistic content but may discard fine-grained acoustic cues essential for speaker discrimination and paralinguistic understanding. Encoder-free Speech-LLMs instead map Mel-spectrogram features directly into the LLM input space through lightweight embedding layers, enabling the LLM to learn from low-level acoustic features. However, systematic pretraining strategies for encoder-free Speech-LLMs remain underexplored, limiting their ability to compensate for the absence of large-scale pretrained speech encoders. We propose metadata-supervised pretraining (MSP), which leverages speech attributes such as speaker identity and emotion to develop speaker-discriminative and paralinguistic capabilities. We further introduce speaker-aware utterance composition (SAUC) to strengthen speaker discrimination and apply random span masking to regularize pretraining. We primarily evaluate our approach on joint ASR and speaker diarization in multi-speaker conversations, complemented by experiments on paralinguistic speech-understanding tasks. Under matched training-data conditions, our encoder-free model outperforms its randomly initialized encoder-based counterpart. With limited metadata-annotated data, it is competitive with models using speech encoders pretrained on substantially larger corpora, outperforming them in several settings. These results demonstrate the potential of encoder-free architectures for building native multimodal LLMs that acquire diverse speech capabilities.

Modern neural text-to-speech (TTS) systems achieve remarkable acoustic fidelity but act as black boxes, offering little interpretable control over the vocal tract filter. We propose a controllable source-filter TTS architecture grounded in articulatory kinematics. An Acoustic-to-Articulatory Inversion (AAI) model, enhanced by large-scale pretrained representations, generates kinematic pseudo-trajectories for a large TTS corpus. These trajectories condition the filter response, while predicted pitch and energy contours parameterise the glottal source. Source and filter are predicted independently, and the source is refined by an Optimal Transport Conditional Flow Matching (OT-CFM) module before recombination into the final spectrogram. Our model achieves intelligibility and naturalness competitive with similarly sized baselines, with only a modest spectral fidelity cost in exchange for explicit control. Evaluations reveal clear source-filter disentanglement, enabling stable prosodic scaling and cross-speaker source/filter recombination, where F0 remains tied to the source speaker while vocal-tract characteristics follow the filter speaker. Finally, direct manipulation of articulatory trajectories enables fine-grained control, such as accent modification, offering a new direction for interpretable speech synthesis. Audio samples: https://coding-phoenix-12.github.io/ArticulatorySFTTS/

In one-shot training-free voice conversion (VC), the source and reference utterances may contain different linguistic content, so reliable frame-level correspondence between them cannot be assumed. We propose StateVC, which jointly defines a common set of local regions from pooled frame-level WavLM representations of the source and reference utterances; we refer to these regions as states. These shared states are obtained by fitting a pair-specific Gaussian mixture model to the pooled representations, without explicit source--reference frame matching. Within each state, StateVC estimates a source-to-reference mean shift in the original WavLM space. Source-frame posterior probabilities then combine the state-specific shifts so that different frames can receive different local updates. For the LibriSpeech one-shot protocol, StateVC achieves the lowest word error rate (WER) and character error rate (CER) among the evaluated systems, at 8.01% and 3.22%, respectively, with a speaker similarity (SIM) of 0.9512. It also achieves the highest mean perceived speaker similarity among the evaluated systems and the highest mean naturalness among the evaluated training-free systems.