Advancing Multi-talker ASR Performance with Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Shi, Mohan, Jin, Zengrui, Xu, Yaoxun, Xu, Yong, Zhang, Shi-Xiong, Wei, Kun, Shao, Yiwen, Zhang, Chunlei, Yu, Dong
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Audio and Speech Processing Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Multi-Channel Multi-Speaker ASR Using Target Speaker's Solo Segment
von: Shao, Yiwen, et al.
Veröffentlicht: (2024)

Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR
von: Wang, Weiqing, et al.
Veröffentlicht: (2025)

RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarios
von: Shao, Yiwen, et al.
Veröffentlicht: (2023)

Efficient Scaling for LLM-based ASR
von: Mu, Bingshen, et al.
Veröffentlicht: (2025)

LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
von: Jin, Zengrui, et al.
Veröffentlicht: (2024)

SpatialEmb: Extract and Encode Spatial Information for 1-Stage Multi-channel Multi-speaker ASR on Arbitrary Microphone Arrays
von: Shao, Yiwen, et al.
Veröffentlicht: (2026)

META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR
von: Wang, Jinhan, et al.
Veröffentlicht: (2024)

Text-aware Speech Separation for Multi-talker Keyword Spotting
von: Li, Haoyu, et al.
Veröffentlicht: (2024)

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

Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long Audio
von: Shi, Mohan, et al.
Veröffentlicht: (2025)

HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models
von: Mu, Bingshen, et al.
Veröffentlicht: (2024)

CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR
von: Shankar, Natarajan Balaji, et al.
Veröffentlicht: (2025)

Comparing Unsupervised and Supervised Semantic Speech Tokens: A Case Study of Child ASR
von: Shi, Mohan, et al.
Veröffentlicht: (2025)

Listening to Multi-talker Conversations: Modular and End-to-end Perspectives
von: Raj, Desh
Veröffentlicht: (2024)

MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios
von: Wang, Shuai, et al.
Veröffentlicht: (2025)

DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Models
von: Li, Li, et al.
Veröffentlicht: (2026)

Word Error Rate Definitions and Algorithms for Long-Form Multi-talker Speech Recognition
von: von Neumann, Thilo, et al.
Veröffentlicht: (2025)

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
von: Zhuo, Jianheng, et al.
Veröffentlicht: (2025)

Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation
von: Wang, Huimeng, et al.
Veröffentlicht: (2024)

Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing
von: Wang, Mengqi, et al.
Veröffentlicht: (2025)

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

Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision
von: Li, Zhaoqing, et al.
Veröffentlicht: (2025)

Auden-Voice: General-Purpose Voice Encoder for Speech and Language Understanding
von: Huo, Mingyue, et al.
Veröffentlicht: (2025)

Augmenting Open-Vocabulary Dysarthric Speech Assessment with Human Perceptual Supervision
von: Jia, Kaimeng, et al.
Veröffentlicht: (2025)

Multiplexing Neural Audio Watermarks
von: Yuan, Zheqi, et al.
Veröffentlicht: (2025)

SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor
von: Yang, Chenyu, et al.
Veröffentlicht: (2024)

Efficient Multilingual ASR Finetuning via LoRA Language Experts
von: Li, Jiahong, et al.
Veröffentlicht: (2025)

TTA: Transcribe, Translate and Alignment for Cross-lingual Speech Representation
von: Liu, Wei, et al.
Veröffentlicht: (2025)

Balancing Speech Understanding and Generation Using Continual Pre-training for Codec-based Speech LLM
von: Shi, Jiatong, et al.
Veröffentlicht: (2025)

Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask
von: Wang, Tianzi, et al.
Veröffentlicht: (2025)

Qwen3-ASR Technical Report
von: Shi, Xian, et al.
Veröffentlicht: (2026)

HydraFormer: One Encoder For All Subsampling Rates
von: Xu, Yaoxun, et al.
Veröffentlicht: (2024)

Semi-supervised Learning for Code-Switching ASR with Large Language Model Filter
von: Xi, Yu, et al.
Veröffentlicht: (2024)

SA-SOT: Speaker-Aware Serialized Output Training for Multi-Talker ASR
von: Fan, Zhiyun, et al.
Veröffentlicht: (2024)

BANC: Towards Efficient Binaural Audio Neural Codec for Overlapping Speech
von: Ratnarajah, Anton, et al.
Veröffentlicht: (2023)

WAKE: Watermarking Audio with Key Enrichment
von: Xu, Yaoxun, et al.
Veröffentlicht: (2025)

Phonemes vs. Projectors: An Investigation of Speech-Language Interfaces for LLM-based ASR
von: Li, Ziwei, et al.
Veröffentlicht: (2026)

Unfolding A Few Structures for The Many: Memory-Efficient Compression of Conformer and Speech Foundation Models
von: Li, Zhaoqing, et al.
Veröffentlicht: (2025)

Large Language Models based ASR Error Correction for Child Conversations
von: Xu, Anfeng, et al.
Veröffentlicht: (2025)

Index-ASR Technical Report
von: Song, Zheshu, et al.
Veröffentlicht: (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
ui	"standard"
VUFIND_SESSION	"914e4c2a006e7518e56078f8239b1725"
language	"de"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790782771.9895 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "914e4c2a006e7518e56078f8239b1725" ]`]
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; VUFIND_SESSION=914e4c2a006e7518e56078f8239b1725; 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	"216.73.216.147"
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	"36721"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2408_17431/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2408_17431/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790782771.9789
REQUEST_TIME	1790782771

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler