Measuring Prosody Diversity in Zero-Shot TTS: A New Metric, Benchmark, and Exploration

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Yifan, Han, Bing, Wang, Hui, Zhou, Long, Wang, Wei, Cui, Mingyu, Tan, Xu, Chen, Xie
Formato:	Preprint
Publicado:	2025
Materias:	Audio and Speech Processing
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Expressive Zero-Shot Speech Synthesis with Hierarchical Prosody Modeling
por: Jiang, Yuepeng, et al.
Publicado: (2024)

E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
por: Eskimez, Sefik Emre, et al.
Publicado: (2024)

PRESENT: Zero-Shot Text-to-Prosody Control
por: Lam, Perry, et al.
Publicado: (2024)

Time-Layer Adaptive Alignment for Speaker Similarity in Flow-Matching Based Zero-Shot TTS
por: Li, Haoyu, et al.
Publicado: (2025)

Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
por: Jiang, Ziyue, et al.
Publicado: (2023)

IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
por: Deng, Wei, et al.
Publicado: (2025)

Zero-Shot TTS With Enhanced Audio Prompts: Bsc Submission For The 2026 Wildspoof Challenge TTS Track
por: Giraldo, Jose, et al.
Publicado: (2026)

Intelli-Z: Toward Intelligible Zero-Shot TTS
por: Jung, Sunghee, et al.
Publicado: (2024)

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training
por: Yang, Yifan, et al.
Publicado: (2026)

Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learning
por: Zhao, Junchuan, et al.
Publicado: (2025)

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM
por: Yu, Jiawei, et al.
Publicado: (2024)

Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion
por: Chen, Zhengyang, et al.
Publicado: (2024)

No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTS
por: Shin, Seungyoun, et al.
Publicado: (2025)

Combining Masked Language Modeling and Cross-Modal Contrastive Learning for Prosody-Aware TTS
por: Borodin, Kirill, et al.
Publicado: (2026)

WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark
por: Ma, Linhan, et al.
Publicado: (2024)

Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations
por: Jeon, Yejin, et al.
Publicado: (2024)

Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting
por: Han, Wooseok, et al.
Publicado: (2024)

VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation
por: Peng, Puyuan, et al.
Publicado: (2025)

Traceable TTS: Toward Watermark-Free TTS with Strong Traceability
por: Zhao, Yuxiang, et al.
Publicado: (2025)

DiaMoE-TTS: A Unified IPA-Based Dialect TTS Framework with Mixture-of-Experts and Parameter-Efficient Zero-Shot Adaptation
por: Chen, Ziqi, et al.
Publicado: (2025)

The Codec Language Model-based Zero-Shot Spontaneous Style TTS System for CoVoC Challenge 2024
por: Zhou, Shuoyi, et al.
Publicado: (2024)

HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling
por: Wang, Chunhui, et al.
Publicado: (2024)

StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion
por: Li, Yinghao Aaron, et al.
Publicado: (2024)

ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis
por: Li, Haitao, et al.
Publicado: (2026)

Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition
por: Chevi, Rendi, et al.
Publicado: (2024)

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models
por: Lee, Kyowoon, et al.
Publicado: (2025)

An Exploration of ECAPA-TDNN and x-vector Speaker Representations in Zero-shot Multi-speaker TTS
por: Kunešová, Marie, et al.
Publicado: (2025)

CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech
por: Kim, Jaehyeon, et al.
Publicado: (2024)

Scaling NVIDIA's Multi-speaker Multi-lingual TTS Systems with Zero-Shot TTS to Indic Languages
por: Arora, Akshit, et al.
Publicado: (2024)

Zero-shot Cross-lingual Voice Transfer for TTS
por: Biadsy, Fadi, et al.
Publicado: (2024)

MPE-TTS: Customized Emotion Zero-Shot Text-To-Speech Using Multi-Modal Prompt
por: Wu, Zhichao, et al.
Publicado: (2025)

DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles
por: Liu, Jiaxuan, et al.
Publicado: (2024)

FireRedTTS-1S: An Upgraded Streamable Foundation Text-to-Speech System
por: Guo, Hao-Han, et al.
Publicado: (2025)

Voice Impression Control in Zero-Shot TTS
por: Fujita, Kenichi, et al.
Publicado: (2025)

An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTS
por: Wang, Xiaofei, et al.
Publicado: (2024)

IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
por: Zhou, Siyi, et al.
Publicado: (2025)

DINO-VITS: Data-Efficient Zero-Shot TTS with Self-Supervised Speaker Verification Loss for Noise Robustness
por: Pankov, Vikentii, et al.
Publicado: (2023)

Expressive Prompting: Improving Emotion Intensity and Speaker Consistency in Zero-Shot TTS
por: Wang, Haoyu, et al.
Publicado: (2024)

Position: Towards Responsible Evaluation for Text-to-Speech
por: Yang, Yifan, et al.
Publicado: (2025)

Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS
por: Seo, Deokjin, et al.
Publicado: (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	"8e9c674bfa6c224f50f0861b8975c5e8"
ui	"standard"
language	"es"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790882260.3758 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "8e9c674bfa6c224f50f0861b8975c5e8" ]`]
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=8e9c674bfa6c224f50f0861b8975c5e8; ui=standard; language=es"
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	"48802"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2509_19928/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_19928/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790882260.3663
REQUEST_TIME	1790882260

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler