Cover Image

Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gu, Zijin, Likhomanenko, Tatiana, Jaitly, Navdeep
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning Sound Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SpeakStream: Streaming Text-to-Speech with Interleaved Data
by: Bai, Richard He, et al.
Published: (2025)

dMel: Speech Tokenization made Simple
by: Bai, Richard He, et al.
Published: (2024)

Revisiting ASR Error Correction with Specialized Models
by: Gu, Zijin, et al.
Published: (2024)

ChipChat: Low-Latency Cascaded Conversational Agent in MLX
by: Likhomanenko, Tatiana, et al.
Published: (2025)

Closing the Gap Between Text and Speech Understanding in LLMs
by: Cuervo, Santiago, et al.
Published: (2025)

Unsupervised ASR via Cross-Lingual Pseudo-Labeling
by: Likhomanenko, Tatiana, et al.
Published: (2023)

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts
by: Jin, Hojun, et al.
Published: (2025)

An Effective Mixture-Of-Experts Approach For Code-Switching Speech Recognition Leveraging Encoder Disentanglement
by: Yang, Tzu-Ting, et al.
Published: (2024)

Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting
by: Yang, Chao-Han Huck, et al.
Published: (2023)

RNN-Transducer-based Losses for Speech Recognition on Noisy Targets
by: Bataev, Vladimir
Published: (2025)

Style Mixture of Experts for Expressive Text-To-Speech Synthesis
by: Jawaid, Ahad, et al.
Published: (2024)

Decoder-only Conformer with Modality-aware Sparse Mixtures of Experts for ASR
by: Lee, Jaeyoung, et al.
Published: (2026)

Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
by: Hu, Yuchen, et al.
Published: (2024)

Towards End-to-End Training of Automatic Speech Recognition for Nigerian Pidgin
by: Rufai, Amina Mardiyyah, et al.
Published: (2020)

MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation
by: Chen, Szu-Chi, et al.
Published: (2026)

Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition
by: Su, Hsuan, et al.
Published: (2024)

Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition
by: Yang, Chao-Han Huck, et al.
Published: (2024)

DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective
by: Chi, Hyung Gun, et al.
Published: (2025)

Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models
by: Hu, Yuchen, et al.
Published: (2024)

Leveraging Mixture of Experts for Improved Speech Deepfake Detection
by: Negroni, Viola, et al.
Published: (2024)

Low-Rank and Sparse Model Merging for Multi-Lingual Speech Recognition and Translation
by: Zhao, Qiuming, et al.
Published: (2025)

Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognition
by: Singh, Satwinder, et al.
Published: (2025)

FlashSpeech: Efficient Zero-Shot Speech Synthesis
by: Ye, Zhen, et al.
Published: (2024)

STTATTS: Unified Speech-To-Text And Text-To-Speech Model
by: Toyin, Hawau Olamide, et al.
Published: (2024)

Enhancing Automatic Speech Recognition Through Integrated Noise Detection Architecture
by: Singh, Karamvir
Published: (2025)

LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation
by: Kamahori, Keisuke, et al.
Published: (2025)

WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper
by: Akinrintoyo, Emmanuel, et al.
Published: (2025)

Advancing Speech Understanding in Speech-Aware Language Models with GRPO
by: Elmakies, Avishai, et al.
Published: (2025)

VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild
by: Peng, Puyuan, et al.
Published: (2024)

Speech Command Recognition Using LogNNet Reservoir Computing for Embedded Systems
by: Izotov, Yuriy, et al.
Published: (2025)

Speech Emotion Recognition Using CNN and Its Use Case in Digital Healthcare
by: Nigar, Nishargo
Published: (2024)

Focal Loss based Residual Convolutional Neural Network for Speech Emotion Recognition
by: Tripathi, Suraj, et al.
Published: (2019)

Unsupervised Speech Segmentation: A General Approach Using Speech Language Models
by: Elmakies, Avishai, et al.
Published: (2025)

TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment
by: Kim, Taesoo, et al.
Published: (2025)

NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
by: Ju, Zeqian, et al.
Published: (2024)

Scaling Ambiguity: Augmenting Human Annotation in Speech Emotion Recognition with Audio-Language Models
by: Zhang, Wenda, et al.
Published: (2026)

Bridging Modalities: Knowledge Distillation and Masked Training for Translating Multi-Modal Emotion Recognition to Uni-Modal, Speech-Only Emotion Recognition
by: Muaz, Muhammad, et al.
Published: (2024)

Autoregressive Diffusion Transformer for Text-to-Speech Synthesis
by: Liu, Zhijun, et al.
Published: (2024)

Real-time Speech Summarization for Medical Conversations
by: Le-Duc, Khai, et al.
Published: (2024)

Enhanced Speech Emotion Recognition with Efficient Channel Attention Guided Deep CNN-BiLSTM Framework
by: Kundu, Niloy Kumar, et al.
Published: (2024)