Speech Recognition Model Improves Text-to-Speech Synthesis using Fine-Grained Reward

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Guansu, Sun, Peijie
Formato:	Preprint
Publicado:	2025
Materias:	Audio and Speech Processing Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis
por: Do, Cong-Thanh, et al.
Publicado: (2024)

Speech Recognition Rescoring with Large Speech-Text Foundation Models
por: Shivakumar, Prashanth Gurunath, et al.
Publicado: (2024)

Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation
por: Huang, Ruizhe, et al.
Publicado: (2024)

Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition
por: Cornell, Samuele, et al.
Publicado: (2024)

TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis
por: Wang, Xi, et al.
Publicado: (2026)

Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning
por: Chien, Chung-Ming, et al.
Publicado: (2024)

VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning
por: Peng, Yifan, et al.
Publicado: (2024)

Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text
por: Li, Jinpeng, et al.
Publicado: (2024)

Streaming Speech-to-Confusion Network Speech Recognition
por: Filimonov, Denis, et al.
Publicado: (2023)

Continuous Speech Tokenizer in Text To Speech
por: Li, Yixing, et al.
Publicado: (2024)

Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis
por: Zhou, Kun, et al.
Publicado: (2024)

Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis
por: Yang, Yifan, et al.
Publicado: (2025)

Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
por: Wu, Haibin, et al.
Publicado: (2025)

Improving the Inclusivity of Dutch Speech Recognition by Fine-tuning Whisper on the JASMIN-CGN Corpus
por: Shekoufandeh, Golshid, et al.
Publicado: (2025)

UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Models
por: Tu, Wenming, et al.
Publicado: (2025)

DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment
por: Lu, Ke-Han, et al.
Publicado: (2024)

MTLM: Incorporating Bidirectional Text Information to Enhance Language Model Training in Speech Recognition Systems
por: Meng, Qingliang, et al.
Publicado: (2025)

Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection
por: Lin, Hsi-Che, et al.
Publicado: (2024)

FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching
por: Wang, Hui, et al.
Publicado: (2025)

MahaTTS: A Unified Framework for Multilingual Text-to-Speech Synthesis
por: Singh, Jaskaran, et al.
Publicado: (2025)

Exploring Effective Distillation of Self-Supervised Speech Models for Automatic Speech Recognition
por: Wang, Yujin, et al.
Publicado: (2022)

Speaker-Aware Simulation Improves Conversational Speech Recognition
por: Gedeon, Máté, et al.
Publicado: (2026)

Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning
por: Fang, Yangui, et al.
Publicado: (2025)

Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition
por: Tseng, Yuan, et al.
Publicado: (2025)

Evaluating Speech-to-Text x LLM x Text-to-Speech Combinations for AI Interview Systems
por: Allbert, Rumi, et al.
Publicado: (2025)

TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding
por: Huo, Mingyue, et al.
Publicado: (2026)

SpeechColab Leaderboard: An Open-Source Platform for Automatic Speech Recognition Evaluation
por: Du, Jiayu, et al.
Publicado: (2024)

Improving Multilingual Speech Models on ML-SUPERB 2.0: Fine-tuning with Data Augmentation and LID-Aware CTC
por: Wang, Qingzheng, et al.
Publicado: (2025)

Chain of Correction for Full-text Speech Recognition with Large Language Models
por: Tang, Zhiyuan, et al.
Publicado: (2025)

An Empirical Study of Speech Language Models for Prompt-Conditioned Speech Synthesis
por: Peng, Yifan, et al.
Publicado: (2024)

Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback
por: Chen, Chen, et al.
Publicado: (2024)

Multi-stage Large Language Model Correction for Speech Recognition
por: Pu, Jie, et al.
Publicado: (2023)

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs
por: Futami, Hayato, et al.
Publicado: (2025)

Full-text Error Correction for Chinese Speech Recognition with Large Language Model
por: Tang, Zhiyuan, et al.
Publicado: (2024)

Revisiting Interpolation Augmentation for Speech-to-Text Generation
por: Xu, Chen, et al.
Publicado: (2024)

PhoWhisper: Automatic Speech Recognition for Vietnamese
por: Le, Thanh-Thien, et al.
Publicado: (2024)

Zero-resource Speech Translation and Recognition with LLMs
por: Mundnich, Karel, et al.
Publicado: (2024)

Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization
por: Hu, Yuchen, et al.
Publicado: (2024)

Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model
por: Xue, Jinlong, et al.
Publicado: (2024)

Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages
por: Meng, Yangyang, et al.
Publicado: (2025)

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
language	"es"
VUFIND_SESSION	"c69b2d5e97db57dc91eab9fdbe1895ab"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1791001073.6213 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "c69b2d5e97db57dc91eab9fdbe1895ab" ]`]
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	"language=es; VUFIND_SESSION=c69b2d5e97db57dc91eab9fdbe1895ab; ui=standard"
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	"26732"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2511_17555/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2511_17555/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1791001073.607
REQUEST_TIME	1791001073

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler