AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Lu, Yuxin, Sun, Jiayang, Zhu, Guibo, Cao, Min
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Machine Learning Artificial Intelligence Sound
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

DiffusionTalker: Efficient and Compact Speech-Driven 3D Talking Head via Personalizer-Guided Distillation
von: Chen, Peng, et al.
Veröffentlicht: (2025)

TempoSyncDiff: Distilled Temporally-Consistent Diffusion for Low-Latency Audio-Driven Talking Head Generation
von: Mazumdar, Soumya, et al.
Veröffentlicht: (2026)

EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation
von: Zhu, Tianheng, et al.
Veröffentlicht: (2025)

Incorporating Talker Identity Aids With Improving Speech Recognition in Adversarial Environments
von: Alavilli, Sagarika, et al.
Veröffentlicht: (2024)

PGSTalker: Real-Time Audio-Driven Talking Head Generation via 3D Gaussian Splatting with Pixel-Aware Density Control
von: Zhu, Tianheng, et al.
Veröffentlicht: (2025)

DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generation
von: Novack, Zachary, et al.
Veröffentlicht: (2024)

Learning Frame-Wise Emotion Intensity for Audio-Driven Talking-Head Generation
von: Xu, Jingyi, et al.
Veröffentlicht: (2024)

MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation
von: Li, Haitian, et al.
Veröffentlicht: (2026)

Logit Distillation on Manifolds: Mapping by Learning
von: Yang, Yiru, et al.
Veröffentlicht: (2026)

Uncertainty-Aware 3D Emotional Talking Face Synthesis with Emotion Prior Distillation
von: Shen, Nanhan, et al.
Veröffentlicht: (2026)

Enabling Automatic Self-Talk Detection via Earables
von: Lee, Euihyeok, et al.
Veröffentlicht: (2025)

Presto! Distilling Steps and Layers for Accelerating Music Generation
von: Novack, Zachary, et al.
Veröffentlicht: (2024)

DreamHead: Learning Spatial-Temporal Correspondence via Hierarchical Diffusion for Audio-driven Talking Head Synthesis
von: Hong, Fa-Ting, et al.
Veröffentlicht: (2024)

ConceptCaps: a Distilled Concept Dataset for Interpretability in Music Models
von: Sienkiewicz, Bruno, et al.
Veröffentlicht: (2026)

SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing
von: Tan, Jiaye, et al.
Veröffentlicht: (2025)

MARS: Sound Generation via Multi-Channel Autoregression on Spectrograms
von: Ristori, Eleonora, et al.
Veröffentlicht: (2025)

Survey on the Evaluation of Generative Models in Music
von: Lerch, Alexander, et al.
Veröffentlicht: (2025)

LPIPS-AttnWav2Lip: Generic Audio-Driven lip synchronization for Talking Head Generation in the Wild
von: Chen, Zhipeng, et al.
Veröffentlicht: (2026)

Anchored Cyclic Generation: A Novel Paradigm for Long-Sequence Symbolic Music Generation
von: Cao, Boyu, et al.
Veröffentlicht: (2026)

Mixer is more than just a model
von: Ji, Qingfeng, et al.
Veröffentlicht: (2024)

Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels
von: Weng, Yuzhe, et al.
Veröffentlicht: (2026)

WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation
von: Della Libera, Luca, et al.
Veröffentlicht: (2026)

Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC
von: Kang, Jiawen, et al.
Veröffentlicht: (2024)

QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems
von: Wang, Chien-Chun, et al.
Veröffentlicht: (2025)

Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization
von: Torres, Bernardo, et al.
Veröffentlicht: (2025)

Warm Chat: Diffuse Emotion-aware Interactive Talking Head Avatar with Tree-Structured Guidance
von: Yang, Haijie, et al.
Veröffentlicht: (2025)

VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories
von: Zhang, Qian, et al.
Veröffentlicht: (2026)

CoMoSVC: Consistency Model-based Singing Voice Conversion
von: Lu, Yiwen, et al.
Veröffentlicht: (2024)

TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation
von: Wang, Zhenzhi, et al.
Veröffentlicht: (2025)

ECTSpeech: Enhancing Efficient Speech Synthesis via Easy Consistency Tuning
von: Zhu, Tao, et al.
Veröffentlicht: (2025)

S-SONDO: Self-Supervised Knowledge Distillation for General Audio Foundation Models
von: Adlouni, Mohammed Ali El, et al.
Veröffentlicht: (2026)

FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation
von: Della Libera, Luca, et al.
Veröffentlicht: (2025)

PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis
von: Xie, Yifan, et al.
Veröffentlicht: (2024)

SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis
von: Zhang, Zhisheng, et al.
Veröffentlicht: (2025)

E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
von: Zhang, Zhisheng, et al.
Veröffentlicht: (2025)

Cross-Speaker Encoding Network for Multi-Talker Speech Recognition
von: Kang, Jiawen, et al.
Veröffentlicht: (2024)

Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models
von: Marincione, Davide, et al.
Veröffentlicht: (2025)

Explicit Context-Driven Neural Acoustic Modeling for High-Fidelity RIR Generation
von: Si, Chen, et al.
Veröffentlicht: (2025)

Yin-Yang: Developing Motifs With Long-Term Structure And Controllability
von: Bhandari, Keshav, et al.
Veröffentlicht: (2025)

Mitigating Unauthorized Speech Synthesis for Voice Protection
von: Zhang, Zhisheng, et al.
Veröffentlicht: (2024)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
VUFIND_SESSION	"50f9068104f4da7fa4410d22a59099b3"
ui	"standard"
language	"de"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1791267903.2457 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "50f9068104f4da7fa4410d22a59099b3" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"VUFIND_SESSION=50f9068104f4da7fa4410d22a59099b3; ui=standard; language=de"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.216.28"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"9507"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2605_02948/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2605_02948/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1791267903.2335
REQUEST_TIME	1791267903

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler