Imagen de Portada

Linguistically Informed Tokenization Improves ASR for Underresourced Languages

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Daul, Massimo, Tosolini, Alessio, Bowern, Claire
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Multilingual MFA: Forced Alignment on Low-Resource Related Languages
por: Tosolini, Alessio, et al.
Publicado: (2025)

Data Augmentation and Hyperparameter Tuning for Low-Resource MFA
por: Tosolini, Alessio, et al.
Publicado: (2025)

Linguistically Informed Evaluation of Multilingual ASR for African Languages
por: Chen, Fei-Yueh, et al.
Publicado: (2026)

Morphologically-Informed Tokenizers for Languages with Non-Concatenative Morphology: A case study of Yoloxóchtil Mixtec ASR
por: Crawford, Chris
Publicado: (2025)

MorphPiece : A Linguistic Tokenizer for Large Language Models
por: Jabbar, Haris
Publicado: (2023)

Language Family Matters: Evaluating LLM-Based ASR Across Linguistic Boundaries
por: Zhang, Yuchen, et al.
Publicado: (2026)

Linguistic Profiling of a Neural Language Model
por: Miaschi, Alessio, et al.
Publicado: (2020)

Towards Linguistically-Aware and Language-Independent Tokenization for Large Language Models (LLMs)
por: Rahman, Abrar, et al.
Publicado: (2024)

MLMA: Towards Multilingual ASR With Mamba-based Architectures
por: Ali, Mohamed Nabih, et al.
Publicado: (2025)

Linguistic Loops and Geometric Invariants as a Way to Pre-Verbal Thought?
por: Corradetti, Daniele, et al.
Publicado: (2025)

Linguistic Fingerprint in Transformer Models: How Language Variation Influences Parameter Selection in Irony Detection
por: Mastromattei, Michele, et al.
Publicado: (2024)

Exploring SSL Discrete Tokens for Multilingual ASR
por: Cui, Mingyu, et al.
Publicado: (2024)

New Insights into Optimal Alignment of Acoustic and Linguistic Representations for Knowledge Transfer in ASR
por: Lu, Xugang, et al.
Publicado: (2025)

Improving Contextual ASR via Multi-grained Fusion with Large Language Models
por: Zhou, Shilin, et al.
Publicado: (2025)

Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It)
por: Miaschi, Alessio, et al.
Publicado: (2024)

CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR
por: Shakeel, Muhammad, et al.
Publicado: (2026)

LIEDER: Linguistically-Informed Evaluation for Discourse Entity Recognition
por: Zhu, Xiaomeng, et al.
Publicado: (2024)

Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages
por: Ruzzetti, Elena Sofia, et al.
Publicado: (2023)

Linguistic Entity Masking to Improve Cross-Lingual Representation of Multilingual Language Models for Low-Resource Languages
por: Fernando, Aloka, et al.
Publicado: (2025)

One Token Is Enough: Improving Diffusion Language Models with a Sink Token
por: Zhang, Zihou, et al.
Publicado: (2026)

Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications
por: Cui, Can, et al.
Publicado: (2024)

Linguistic Minimal Pairs Elicit Linguistic Similarity in Large Language Models
por: Zhou, Xinyu, et al.
Publicado: (2024)

Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions
por: Zhang, Kexun, et al.
Publicado: (2024)

LBPE: Long-token-first Tokenization to Improve Large Language Models
por: Lian, Haoran, et al.
Publicado: (2024)

Improving ASR Contextual Biasing with Guided Attention
por: Tang, Jiyang, et al.
Publicado: (2024)

Task Arithmetic with Support Languages for Low-Resource ASR
por: Rafkin, Emma, et al.
Publicado: (2026)

Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models
por: Galatolo, Alessio, et al.
Publicado: (2025)

The Sound of Healthcare: Improving Medical Transcription ASR Accuracy with Large Language Models
por: Adedeji, Ayo, et al.
Publicado: (2024)

UnMASKed: Quantifying Gender Biases in Masked Language Models through Linguistically Informed Job Market Prompts
por: Parra, Iñigo
Publicado: (2024)

Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations
por: Zhao, Yize, et al.
Publicado: (2025)

Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge
por: Cantini, Riccardo, et al.
Publicado: (2025)

Improving Linguistic Diversity of Large Language Models with Possibility Exploration Fine-Tuning
por: Mai, Long, et al.
Publicado: (2024)

Improving Bilingual Capabilities of Language Models to Support Diverse Linguistic Practices in Education
por: Syamkumar, Anand, et al.
Publicado: (2024)

MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization
por: Ahia, Orevaoghene, et al.
Publicado: (2024)

Ethio-ASR: Joint Multilingual Speech Recognition and Language Identification for Ethiopian Languages
por: Abdullah, Badr M., et al.
Publicado: (2026)

Linguistically-Informed Multilingual Instruction Tuning: Is There an Optimal Set of Languages to Tune?
por: Soykan, Gürkan, et al.
Publicado: (2024)

Improving Domain-Specific ASR with LLM-Generated Contextual Descriptions
por: Suh, Jiwon, et al.
Publicado: (2024)

Model-free Speculative Decoding for Transformer-based ASR with Token Map Drafting
por: Ho, Tuan Vu, et al.
Publicado: (2025)

Tokenization Matters: Improving Zero-Shot NER for Indic Languages
por: Pattnayak, Priyaranjan, et al.
Publicado: (2025)

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
por: Su, DiJia, et al.
Publicado: (2025)