PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Banerjee, Adhiraj, Arora, Vipul
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computation and Language Sound
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents
por: Banerjee, Adhiraj, et al.
Publicado: (2025)

WavLink: Compact Audio-Text Embeddings with a Global Whisper Token
por: Kumar, Gokul Karthik, et al.
Publicado: (2026)

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
por: Fang, Zheng, et al.
Publicado: (2026)

AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning
por: Kim, Jongsuk, et al.
Publicado: (2024)

TokenChain: A Discrete Speech Chain via Semantic Token Modeling
por: Wang, Mingxuan, et al.
Publicado: (2025)

AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation
por: Papi, Sara, et al.
Publicado: (2023)

PAST: Phonetic-Acoustic Speech Tokenizer
por: Har-Tuv, Nadav, et al.
Publicado: (2025)

Decoding the Ear: A Framework for Objectifying Expressiveness from Human Preference Through Efficient Alignment
por: Lin, Zhiyu, et al.
Publicado: (2025)

Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction
por: Kim, Minchan, et al.
Publicado: (2024)

Token-Weighted RNN-T for Learning from Flawed Data
por: Keren, Gil, et al.
Publicado: (2024)

Exploring Token-Space Manipulation in Latent Audio Tokenizers
por: Paissan, Francesco, et al.
Publicado: (2026)

DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models
por: Chang, Heng-Jui, et al.
Publicado: (2024)

AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering
por: Kuan, Chun-Yi, et al.
Publicado: (2026)

UALM: Unified Audio Language Model for Understanding, Generation and Reasoning
por: Tian, Jinchuan, et al.
Publicado: (2025)

Assessing Factual Music Comprehension in Large Audio Language Models
por: Lin, Daniel Chenyu, et al.
Publicado: (2025)

Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction
por: Gosai, Advait, et al.
Publicado: (2025)

From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data
por: Kuan, Chun-Yi, et al.
Publicado: (2025)

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
por: Rauch, Lukas, et al.
Publicado: (2025)

RUMAA: Repeat-Aware Unified Music Audio Analysis for Score-Performance Alignment, Transcription, and Mistake Detection
por: Chang, Sungkyun, et al.
Publicado: (2025)

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models
por: He, Peize, et al.
Publicado: (2026)

High-Fidelity Speech Enhancement via Discrete Audio Tokens
por: Lanzendörfer, Luca A., et al.
Publicado: (2025)

TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
por: Tseng, Liang-Hsuan, et al.
Publicado: (2026)

Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation
por: Kim, Eungbeom, et al.
Publicado: (2024)

MAEB: Massive Audio Embedding Benchmark
por: Assadi, Adnan El, et al.
Publicado: (2026)

Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
por: Ghosh, Sreyan, et al.
Publicado: (2025)

Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
por: Segev, Eliya, et al.
Publicado: (2023)

StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
por: Song, Yuhan, et al.
Publicado: (2025)

Synthetic Audio Helps for Cognitive State Tasks
por: Soubki, Adil, et al.
Publicado: (2025)

Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications
por: Kudlur, Manjunath, et al.
Publicado: (2026)

Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization
por: Della Libera, Luca, et al.
Publicado: (2026)

Lossless Token Sequence Compression via Meta-Tokens
por: Harvill, John, et al.
Publicado: (2025)

AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension
por: Yang, Qian, et al.
Publicado: (2024)

Learning When to Think While Listening in Large Audio-Language Models
por: Song, Zhiyuan, et al.
Publicado: (2026)

EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
por: Chen, Wenxi, et al.
Publicado: (2024)

CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer
por: Takeuchi, Daiki, et al.
Publicado: (2025)

Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data
por: Kumar, Gokul Karthik, et al.
Publicado: (2025)

Aligning Spoken Dialogue Models from User Interactions
por: Wu, Anne, et al.
Publicado: (2025)

Improving Text-To-Audio Models with Synthetic Captions
por: Kong, Zhifeng, et al.
Publicado: (2024)

TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
por: Tseng, Liang-Hsuan, et al.
Publicado: (2025)

ETTA: Elucidating the Design Space of Text-to-Audio Models
por: Lee, Sang-gil, et al.
Publicado: (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
ui	"standard"
language	"es"
VUFIND_SESSION	"2d78db941e90c22ca322bd60c2a2e979"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790854435.7678 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "2d78db941e90c22ca322bd60c2a2e979" ]`]
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	"ui=standard; language=es; VUFIND_SESSION=2d78db941e90c22ca322bd60c2a2e979"
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	"216.73.216.147"
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	"34660"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2605_06582/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_06582/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790854435.7634
REQUEST_TIME	1790854435

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler