Script collapse in multilingual ASR: A reference-free metric and 100-pair benchmark

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Rahman, Hanif
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Sound Audio and Speech Processing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A two-stage transliteration approach to improve performance of a multilingual ASR
di: Kumar, Rohit
Pubblicazione: (2024)

Bridging the gap: A comparative exploration of Speech-LLM and end-to-end architecture for multilingual conversational ASR
di: Mei, Yuxiang, et al.
Pubblicazione: (2026)

Bengali-Loop: Community Benchmarks for Long-Form Bangla ASR and Speaker Diarization
di: Tabib, H. M. Shadman, et al.
Pubblicazione: (2026)

Target Speaker ASR with Whisper
di: Polok, Alexander, et al.
Pubblicazione: (2024)

Index-ASR Technical Report
di: Song, Zheshu, et al.
Pubblicazione: (2025)

Speech Emotion Recognition with ASR Integration
di: Li, Yuanchao
Pubblicazione: (2026)

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

HypR: A comprehensive study for ASR hypothesis revising with a reference corpus
di: Wang, Yi-Wei, et al.
Pubblicazione: (2023)

Technical Report: A Practical Guide to Kaldi ASR Optimization
di: Hong, Mengze, et al.
Pubblicazione: (2025)

The USTC-NERCSLIP Systems for The ICMC-ASR Challenge
di: Wu, Minghui, et al.
Pubblicazione: (2024)

LUPET: Incorporating Hierarchical Information Path into Multilingual ASR
di: Liu, Wei, et al.
Pubblicazione: (2024)

persoDA: Personalized Data Augmentation for Personalized ASR
di: Parada, Pablo Peso, et al.
Pubblicazione: (2025)

Speaker Adaptation for Quantised End-to-End ASR Models
di: Zhao, Qiuming, et al.
Pubblicazione: (2024)

Comparative Analysis of ASR Methods for Speech Deepfake Detection
di: Salvi, Davide, et al.
Pubblicazione: (2024)

Consistency Based Unsupervised Self-training For ASR Personalisation
di: Zhang, Jisi, et al.
Pubblicazione: (2024)

A Unified Denoising and Adaptation Framework for Self-Supervised Bengali Dialectal ASR
di: Biswas, Swadhin, et al.
Pubblicazione: (2025)

Joint ASR and Speaker Role Tagging with Serialized Output Training
di: Xu, Anfeng, et al.
Pubblicazione: (2025)

Learning When to Trust Which Teacher for Weakly Supervised ASR
di: Agrawal, Aakriti, et al.
Pubblicazione: (2023)

Scaling Multi-Talker ASR with Speaker-Agnostic Activity Streams
di: He, Xiluo, et al.
Pubblicazione: (2025)

dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
di: Tian, Wenjie, et al.
Pubblicazione: (2026)

Decoding Strategies for Diffusion-Based ASR: A Systematic Evaluation of Confidence-Based Thresholding
di: Yeo, Jeong Hun, et al.
Pubblicazione: (2026)

Efficient Rehearsal for Continual Learning in ASR via Singular Value Tuning
di: Eeckt, Steven Vander, et al.
Pubblicazione: (2026)

Codec-SUPERB @ SLT 2024: A lightweight benchmark for neural audio codec models
di: Wu, Haibin, et al.
Pubblicazione: (2024)

Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches
di: Mujtaba, Dena, et al.
Pubblicazione: (2025)

Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR
di: Pražák, Aleš, et al.
Pubblicazione: (2025)

Towards Decoupling Frontend Enhancement and Backend Recognition in Monaural Robust ASR
di: Yang, Yufeng, et al.
Pubblicazione: (2024)

Complexity boosted adaptive training for better low resource ASR performance
di: Lu, Hongxuan, et al.
Pubblicazione: (2024)

Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
di: Wang, Weiqing, et al.
Pubblicazione: (2024)

Speaker-Smoothed kNN Speaker Adaptation for End-to-End ASR
di: Li, Shaojun, et al.
Pubblicazione: (2024)

Differentiable K-means for Fully-optimized Discrete Token-based ASR
di: Onda, Kentaro, et al.
Pubblicazione: (2025)

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

CUSIDE-T: Chunking, Simulating Future and Decoding for Transducer based Streaming ASR
di: Zhao, Wenbo, et al.
Pubblicazione: (2024)

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty
di: Xue, Hongfei, et al.
Pubblicazione: (2025)

DQLoRA: A Lightweight Domain-Aware Denoising ASR via Adapter-guided Distillation
di: Yang, Yiru
Pubblicazione: (2025)

End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions
di: Xu, Anfeng, et al.
Pubblicazione: (2026)

BrainWhisperer: Leveraging Large-Scale ASR Models for Neural Speech Decoding
di: Boccato, Tommaso, et al.
Pubblicazione: (2026)

Can We Really Repurpose Multi-Speaker ASR Corpus for Speaker Diarization?
di: Horiguchi, Shota, et al.
Pubblicazione: (2025)

kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
di: Zhou, Jiaming, et al.
Pubblicazione: (2023)

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

DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation
di: Kothawade, Suraj, et al.
Pubblicazione: (2021)