Cover Image

Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pandey, Isha, Mittal, Ashish, Bahuguna, Vartul, Ramakrishnan, Ganesh
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Language translation, and change of accent for speech-to-speech task using diffusion model
by: Mishra, Abhishek, et al.
Published: (2025)

A2TTS: TTS for Low Resource Indian Languages
by: Bhadoriya, Ayush Singh, et al.
Published: (2025)

A Three-Pronged Approach to Cross-Lingual Adaptation with Multilingual LLMs
by: Singh, Vaibhav, et al.
Published: (2024)

SpeechMapper: Speech-to-text Embedding Projector for LLMs
by: Mohapatra, Biswesh, et al.
Published: (2026)

Multilingual Routing in Mixture-of-Experts
by: Bandarkar, Lucas, et al.
Published: (2025)

Automatic Speech Recognition for Hindi
by: Saha, Anish, et al.
Published: (2024)

Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steering
by: Chen, Yuxin, et al.
Published: (2026)

Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights
by: Karthika, N J, et al.
Published: (2025)

LexGen: Domain-aware Multilingual Lexicon Generation
by: Maheshwari, Ayush, et al.
Published: (2024)

Zipper-LoRA: Dynamic Parameter Decoupling for Speech-LLM based Multilingual Speech Recognition
by: Mei, Yuxiang, et al.
Published: (2026)

Efficient infusion of self-supervised representations in Automatic Speech Recognition
by: Prabhu, Darshan, et al.
Published: (2024)

Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition
by: Bagat, Raphaël, et al.
Published: (2025)

Multilingual Phonological Feature Recognition with Self-Supervised Speech Models
by: Hernandez, Abner, et al.
Published: (2026)

Multilingual Extraction and Recognition of Implicit Discourse Relations in Speech and Text
by: Ruby, Ahmed, et al.
Published: (2026)

Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition
by: Gu, Zijin, et al.
Published: (2025)

Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts Models
by: Deng, Guanzhi, et al.
Published: (2026)

Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages
by: Omnilingual ASR team, et al.
Published: (2025)

Lost in Transcription: How Speech-to-Text Errors Derail Code Understanding
by: Havare, Jayant, et al.
Published: (2026)

CodeVaani: A Multilingual, Voice-Based Code Learning Assistant
by: Havare, Jayant, et al.
Published: (2025)

MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder
by: Le-Duc, Khai, et al.
Published: (2024)

Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition
by: Bijoy, Mehedi Hasan, et al.
Published: (2025)

ViSpeR: Multilingual Audio-Visual Speech Recognition
by: Narayan, Sanath, et al.
Published: (2024)

MSNER: A Multilingual Speech Dataset for Named Entity Recognition
by: Meeus, Quentin, et al.
Published: (2024)

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

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

MoE-LPR: Multilingual Extension of Large Language Models through Mixture-of-Experts with Language Priors Routing
by: Zhou, Hao, et al.
Published: (2024)

DICTDIS: Dictionary Constrained Disambiguation for Improved NMT
by: Maheshwari, Ayush, et al.
Published: (2022)

Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps
by: Attanasio, Giuseppe, et al.
Published: (2024)

Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing
by: Huang, Hukai, et al.
Published: (2024)

Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition
by: Lee, Wonjun, et al.
Published: (2026)

Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts
by: Ferraz, Thomas Palmeira, et al.
Published: (2023)

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations
by: Saengthong, Phurich, et al.
Published: (2025)

StructFormer: Document Structure-based Masked Attention and its Impact on Language Model Pre-Training
by: Ponkshe, Kaustubh, et al.
Published: (2024)

EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark
by: Ma, Ziyang, et al.
Published: (2024)

ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition
by: Meng, Qingliang, et al.
Published: (2025)

Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model
by: Li, Chong, et al.
Published: (2025)

Enhancing Indonesian Automatic Speech Recognition: Evaluating Multilingual Models with Diverse Speech Variabilities
by: Adila, Aulia, et al.
Published: (2024)

The Art of Breaking Words: Rethinking Multilingual Tokenizer Design
by: Thakur, Aamod, et al.
Published: (2025)

Learning to Route Languages for Multilingual Policy Optimization
by: Guo, Geyang, et al.
Published: (2026)

Robust Audiovisual Speech Recognition Models with Mixture-of-Experts
by: Wu, Yihan, et al.
Published: (2024)