{"total":27,"rows":[{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148,"area":"moe"},{"id":"2105.03036","title":"SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts","created":"2021-05-07","cited_by_count":48,"area":"moe"},{"id":"2309.13850","title":"Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts","created":"2023-09-25","cited_by_count":29,"area":"moe"},{"id":"2405.13997","title":"Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts","created":"2024-05-22","cited_by_count":24,"area":"moe"},{"id":"2310.14188","title":"A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts","created":"2023-10-22","cited_by_count":23,"area":"moe"},{"id":"2402.02526","title":"CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition","created":"2024-02-04","cited_by_count":23,"area":"moe"},{"id":"2305.15663","title":"Mixture-of-Expert Conformer for Streaming Multilingual ASR","created":"2023-05-25","cited_by_count":17,"area":"moe"},{"id":"2405.14131","title":"Statistical Advantages of Perturbing Cosine Router in Mixture of Experts","created":"2024-05-23","cited_by_count":16,"area":"moe"},{"id":"2401.13875","title":"Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?","created":"2024-01-25","cited_by_count":15,"area":"moe"},{"id":"2310.02629","title":"BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition","created":"2023-10-04","cited_by_count":9,"area":"moe"},{"id":"2409.15905","title":"Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM","created":"2024-09-24","cited_by_count":9,"area":"moe"},{"id":"2309.16178","title":"LAE-ST-MoE: Boosted Language-Aware Encoder Using Speech Translation Auxiliary Task for E2E Code-switching ASR","created":"2023-09-28","cited_by_count":6,"area":"moe"},{"id":"2406.18021","title":"SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR","created":"2024-06-26","cited_by_count":6,"area":"moe"},{"id":"2204.03178","title":"3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition","created":"2022-04-07","cited_by_count":5,"area":"moe"},{"id":"2404.16407","title":"U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF","created":"2024-04-25","cited_by_count":5,"area":"moe"},{"id":"2502.10447","title":"MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition","created":"2025-02-11","cited_by_count":4,"area":"moe"},{"id":"2507.05724","title":"Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition","created":"2025-07-08","cited_by_count":4,"area":"moe"},{"id":"2607.14530","title":"xHC: Expanded Hyper-Connections","created":"2026-07-16","cited_by_count":4,"area":"moe"},{"id":"2209.08326","title":"Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition","created":"2022-09-17","cited_by_count":3,"area":"moe"},{"id":"2407.18581","title":"Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing","created":"2024-07-26","cited_by_count":2,"area":"moe"},{"id":"2409.02050","title":"Enhancing Code-Switching Speech Recognition with LID-Based Collaborative Mixture of Experts Model","created":"2024-09-03","cited_by_count":2,"area":"moe"},{"id":"2412.17507","title":"UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition","created":"2024-12-23","cited_by_count":1,"area":"moe"},{"id":"2509.13093","title":"GLAD: Global-Local Aware Dynamic Mixture-of-Experts for Multi-Talker ASR","created":"2025-09-16","cited_by_count":1,"area":"moe"},{"id":"2602.01967","title":"Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition","created":"2026-02-02","cited_by_count":1,"area":"moe"},{"id":"2602.12546","title":"Decoder-only Conformer with Modality-aware Sparse Mixtures of Experts for ASR","created":"2026-02-13","cited_by_count":0,"area":"moe"},{"id":"2607.01566","title":"H-SAGE: Holistic Speaker-Aware Guided Experts for MoE-based Multi-Talker ASR","created":"2026-07-02","cited_by_count":0,"area":"moe"},{"id":"2610.16579","title":"LLM-HB: Language-Aware LLM-Guided Hotword Biasing for Code-Switching ASR","created":"2026-10-12","cited_by_count":0,"area":"moe"}],"next_cursor":null}