Accelerating Diffusion Transformer-Based Text-to-Speech with Transformer Layer Caching

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Sakpiboonchit, Siratish
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Audio and Speech Processing Sound
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer
di: Liu, Huadai, et al.
Pubblicazione: (2023)

SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models
di: Yang, Dongchao, et al.
Pubblicazione: (2024)

Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers
di: Lin, Jackie, et al.
Pubblicazione: (2026)

Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment
di: Choi, Jeongsoo, et al.
Pubblicazione: (2025)

Central Kurdish Text-to-Speech Synthesis with Novel End-to-End Transformer Training
di: Ahmad, Hawraz A., et al.
Pubblicazione: (2024)

VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis
di: Jung, Jaemin, et al.
Pubblicazione: (2024)

EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer
di: Hai, Jiarui, et al.
Pubblicazione: (2024)

Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer
di: Hou, Siyuan, et al.
Pubblicazione: (2024)

Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
di: Zheng, Qixi, et al.
Pubblicazione: (2025)

DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformers
di: Guimarães, Heitor R., et al.
Pubblicazione: (2025)

VoiceTailor: Lightweight Plug-In Adapter for Diffusion-Based Personalized Text-to-Speech
di: Kim, Heeseung, et al.
Pubblicazione: (2024)

Investigating Group Relative Policy Optimization for Diffusion Transformer based Text-to-Audio Generation
di: Gu, Yi, et al.
Pubblicazione: (2026)

EmoFormer: A Text-Independent Speech Emotion Recognition using a Hybrid Transformer-CNN model
di: Hasan, Rashedul, et al.
Pubblicazione: (2025)

SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models
di: Yang, Dongchao, et al.
Pubblicazione: (2024)

Study of Lightweight Transformer Architectures for Single-Channel Speech Enhancement
di: Zhao, Haixin, et al.
Pubblicazione: (2025)

Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech
di: de Groot, Dimme, et al.
Pubblicazione: (2025)

Post-Training Quantization for Audio Diffusion Transformers
di: Khandelwal, Tanmay, et al.
Pubblicazione: (2025)

LORT: Locally Refined Convolution and Taylor Transformer for Monaural Speech Enhancement
di: Wang, Junyu, et al.
Pubblicazione: (2025)

FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer
di: Wang, Haoxu, et al.
Pubblicazione: (2025)

VoiceRestore: Flow-Matching Transformers for Speech Recording Quality Restoration
di: Kirdey, Stanislav
Pubblicazione: (2025)

TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
di: Saijo, Kohei, et al.
Pubblicazione: (2024)

Llasa+: Free Lunch for Accelerated and Streaming Llama-Based Speech Synthesis
di: Tian, Wenjie, et al.
Pubblicazione: (2025)

Complex Image-Generative Diffusion Transformer for Audio Denoising
di: Li, Junhui, et al.
Pubblicazione: (2024)

An Empirical Study on the Impact of Positional Encoding in Transformer-based Monaural Speech Enhancement
di: Zhang, Qiquan, et al.
Pubblicazione: (2024)

ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers
di: Gu, Yuzhe, et al.
Pubblicazione: (2024)

DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech
di: Zhang, Xu, et al.
Pubblicazione: (2026)

LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space
di: Xin, Detai, et al.
Pubblicazione: (2026)

Evaluating Self-Supervised Speech Models via Text-Based LLMS
di: Maekaku, Takashi, et al.
Pubblicazione: (2025)

Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis
di: Tu, Zehai, et al.
Pubblicazione: (2024)

Improving Musical Accompaniment Co-creation via Diffusion Transformers
di: Nistal, Javier, et al.
Pubblicazione: (2024)

EDSep: An Effective Diffusion-Based Method for Speech Source Separation
di: Dong, Jinwei, et al.
Pubblicazione: (2025)

Vector Quantized Diffusion Model Based Speech Bandwidth Extension
di: Fang, Yuan, et al.
Pubblicazione: (2024)

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers
di: Lin, Tzu-Quan, et al.
Pubblicazione: (2025)

TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking
di: Zhou, Junzuo, et al.
Pubblicazione: (2024)

UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding
di: Du, Chenpeng, et al.
Pubblicazione: (2023)

Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models
di: Jing, Xin, et al.
Pubblicazione: (2024)

Wireless Hearables With Programmable Speech AI Accelerators
di: Itani, Malek, et al.
Pubblicazione: (2025)

Device Feature based on Graph Fourier Transformation with Logarithmic Processing For Detection of Replay Speech Attacks
di: He, Mingrui, et al.
Pubblicazione: (2024)

Zero-Shot Text-to-Speech from Continuous Text Streams
di: Dang, Trung, et al.
Pubblicazione: (2024)

Advancing Electrolaryngeal Speech Enhancement Through Speech-Text Representation Learning
di: Ma, Ding, et al.
Pubblicazione: (2026)

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	"d5c7f7b00ed16a6acbd2047a6c635643"
ui	"standard"
language	"it"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790960333.471 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "d5c7f7b00ed16a6acbd2047a6c635643" ]`]
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=d5c7f7b00ed16a6acbd2047a6c635643; ui=standard; language=it"
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	"216.73.217.142"
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	"32417"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2509_08696/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2509_08696/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790960333.4575
REQUEST_TIME	1790960333

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler