Talking Avatars, Smarter TTS, and the Challenge of Multi-Party Dialogue

We present Kandinsky S2V 1.0, an open family of speech-to-video models for controllable audio-driven human animation, comprising Kandinsky S2V 1.0 Lite (2B parameters) and Kandinsky S2V 1.0 Pro (21B parameters). From a single reference image, a speech waveform, and a text prompt, the models generate long-form 25 FPS video in which lip motion, expression, pose, and gesture follow the speech. The architecture draws text and audio conditioning from one Qwen2.5-Omni model and adds a reference-aware three-scale visual memory. Training starts from the Kandinsky 5.0 Video foundation models [1] and combines mixed reference-memory layouts with an area-adaptive face loss. The training corpus contains 1.17M single-speaker clips selected by active-speaker detection, with captions generated directly in English and Russian. A side-by-side human evaluation against the strongest open-source baseline and two proprietary commercial models shows that Kandinsky S2V 1.0 Pro performs comparably to or better than these models on average and is also preferred for lip synchronization. On common speech to video benchmarks, Kandinsky S2V 1.0 Lite and Kandinsky S2V 1.0 Pro rank among the top performing models according to mean rank over five reported metrics. Beyond the base models, we provide π-Flow distilled variants of both Kandinsky S2V 1.0 Lite and Kandinsky S2V 1.0 Pro. The distilled Kandinsky S2V 1.0 Pro model generates video in 16 sampling steps without classifier-free guidance, achieving a 5.4 times end-to-end speedup over the base model, while matching or exceeding it on nearly all reported benchmark metrics. To accelerate open research and deployment in speech-to-video generation, we release the code, model checkpoints, and diffusers integration under the MIT license.

Lipreading remains challenging due to the inherent ambiguity of visual speech cues and their sensitivity to head pose and video resolution. In this work, we propose FLARE, a framework for robust visual speech representation learning via cross-modal distillation and joint face-lip modeling. FLARE leverages semantically rich Whisper representations as the acoustic teacher signal, converting them into discrete distillation targets through a random-projection quantizer and pretraining the model with a masked prediction objective. To capture complementary visual information, FLARE employs a dual-stream architecture that jointly processes lip region-of-interest (ROI) and full-face inputs, where the lip stream captures finegrained articulatory motion and the face stream encodes broader facial dynamics. During pretraining, auxiliary audio input is incorporated to facilitate cross-modal alignment, and modality dropout is applied to encourage robust visual-only representations. For downstream lipreading, FLARE serves as a visual encoder coupled with either a lightweight Transformer decoder or an LLM-based decoder. Evaluated on LRS2, LRS3, and the out-of-domain WildVSR benchmark, FLARE achieves strong lipreading performance, with word error rates of 11.7%, 13.2%, and 34.3%, respectively. A progressive design study confirms the contribution of each major component. Further analyses demonstrate that joint face-lip modeling improves robustness under degraded video resolution and large head pose variation, while yielding more phoneme-discriminative visual representations. Code and pretrained models are available at https://github.com/jxzhanggg/FLARE.

Text-to-speech (TTS) based on masked diffusion models (MDMs) achieves competitive zero-shot speech synthesis performance. Unlike autoregressive (AR) models, MDMs define a corruption process that maps clean speech-token sequences to masked maps and learn a reverse denoising process to recover the reference tokens. However, MDMs commit to intermediate predictions that cannot be revised in subsequent inference steps. Consequently, prediction errors accumulate and propagate, degrading synthesized speech quality. We present Revise-TTS, a single-stage framework that applies hierarchical binary quantization (HBQ) and generative refinement networks (GRN) to zero-shot speech generation. First, we replace finite scalar quantization (FSQ) with HBQ to introduce a scalable binary representation for speech tokens with an explicit coarse-to-fine structure. Second, GRN is trained to reconstruct the token sequence from a mixture of ground-truth and random tokens. During inference, iterative refinement enables self-correction by randomly discarding a small proportion of previously predicted tokens with new predictions. Experiments and ablation studies demonstrate that Revise-TTS achieves competitive zero-shot speech synthesis performance using HBQ. It can further be extended to any MDM-based TTS task as an alternative training and inference method.

Zero-shot text-to-speech (TTS) typically conditions on a short speech prompt, which conveys timbre but provides only limited evidence of a speaker's prosodic patterns. We formulate Long-Prompt Zero-Shot TTS, a task that uses long speech prompts at inference time to reproduce speaker-specific prosody without target-speaker fine-tuning. We introduce LP-TTS-Bench, a bilingual benchmark of 37 speakers with 63.95 prompt hours and 2,728 held-out test utterances. Beyond intelligibility and timbre similarity, LP-TTS-Bench evaluates timing, prominence, intonation, and model-based prosody metrics, enabling multidimensional evaluation of prosody reproduction. As a reference system, we develop LPTTS, whose hierarchical Long-Prompt Encoder compresses long speech prompts into a fixed number of continuous prosody vectors. Experiments show improvements in several prosodic dimensions over a short-prompt baseline, with overall gains as prompt duration increases up to approximately 10 minutes and saturation at longer durations.

Recent full-stream text-to-speech (TTS) models enable low-latency personalized synthesis as input text arrives. However, sustaining generation beyond the lengths seen during training without additional training remains largely unexplored. We systematically analyze VoXtream2, which extends generation by periodically discarding past context while retaining the acoustic prompt. We find that this strategy does not prevent degradation: pronunciation accuracy deteriorates near the end of the training range due to the range of positions in which the model operates rather than the loss of past context, while speaker similarity gradually declines throughout generation. Based on these findings, we propose two training-free modifications that reduce the attention window and strengthen attention to the acoustic prompt. Experiments show that these modifications preserve pronunciation accuracy and speaker similarity throughout long-form generation while retaining the naturalness of the original model. Ablations further show complementary effects of the two modifications.

Voice-based conversational agents are increasingly deployed in real-world settings, where environmental noise often degrades the interactive experience. Therefore, robust acoustic adaptability is essential to maintain natural and intelligible human-computer communication. However, most existing systems remain acoustically insensitive and fail to emulate the human Lombard effect, in which speakers involuntarily adjust their vocal production to preserve intelligibility in the presence of noise. As a result, their communicative reliability degrades under adverse acoustic conditions. To remain intelligible in noisy environments, conversational agents require a mechanism to emulate noise-induced adaptive behavior during synthesis. We propose NIL-TTS, a noise-induced Lombard TTS framework. We integrate a feature-wise linear modulation (FiLM) mechanism into a flow-matching backbone for dynamic vocal adaptation. A two-stage training paradigm is utilized: initial supervised fine-tuning on paired Lombard corpora, followed by Flow-GRPO post-training to optimize for intelligibility. Evaluations confirm that NIL-TTS autonomously adjusts its output in response to varying noise conditions, exhibiting key correlates of the human Lombard effect. Driven by these adaptive modulations, the synthesized speech achieves significant intelligibility improvements that scale proportionally with noise intensity. Ultimately, this work presents a flow-matching and reinforcement learning-based advancement within the adaptive Lombard speech synthesis paradigm for challenging real-world scenarios.

Full-duplex speech systems must decide when to enter, hold, or relinquish the conversational floor, even as multiple speakers overlap or backchannel without taking it. Existing evaluations study dyadic turn-taking or end-to-end agent behavior, but lack a unified, controlled evaluation of genuine floor transitions against confusable non-events in multi-party settings. We introduce MultiPartyTurnBench (MPTB), a benchmark of 240 synthetically generated, channel-separated conversations spanning two to five speakers and six interaction types. MPTB evaluates two complementary tasks: End-of-Turn (EOT) detection distinguishes genuine turn completion from temporary holds, while Interruption (INT) detection distinguishes successful floor takeovers from non-floor-taking speech. Exact event-conditioned annotations enable causal evaluation using false-positive-constrained recall and signed latency. Across acoustic, semantic, and turn-projection baselines, we find a stark asymmetry: learned systems achieve 82.5-92.6% EOT recall at 4.3-11.8% false-positive rates, while INT detection suffers from missed takeovers or excessive false activations. This asymmetry extends to five full-duplex agents which achieve 86.1-95.8% balanced accuracy on turn entry, yet perform near chance (46.9-54.7%) on selective interruption handling. Gemini-3.8-Live yields to 97.7% of backchannels, whereas MiniCPM-o-4.5 yields to only 1.4% of genuine interruptions. These findings establish selective floor control as a distinct, unresolved challenge for reliable multi-party voice interaction.

Feature distillation is usually expected to add to logit distillation. We find that this expectation does not hold for two common feature losses in compact multilingual automatic speech recognition (ASR), and analyze why through their gradients. The gradient of a projection-based loss is orthogonal to the task gradient, while that of Centered Kernel Alignment (CKA), a similarity-based loss, is weakly aligned with it. CKA lowers the word error rate (WER) on non-English languages, but at the expense of data-rich English. Three loss-level remedies (one trained, two probed) all fall short, and the CKA gradient overlaps with the subspace English uses in the shared encoder by 97.5% to 99.5% (about 81% by chance). Guided by this diagnosis, we propose CAFE (Confined-Adapter Feature distillation), which confines the CKA gradient to adapters that English bypasses, addressing the trade-off in the parameters rather than in the loss. On the Open ASR Leaderboard, CAFE lowers the average WER from 8.55% to 8.02%, beats an adapter-only capacity control at 8.51%, and makes English more stable across checkpoints. At 254M parameters, it trails the 0.6B teacher by 2 WER points and is competitive with much larger models across 48 test sets in 24 languages. We use 564k hours of training data and state-of-the-art models to keep the findings relevant to practice.