{"total":11,"rows":[{"id":"2203.12758","title":"Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models","created":"2022-03-23","cited_by_count":19,"area":null},{"id":"2410.09456","title":"Automatic Speech Recognition with BERT and CTC Transformers: A Review","created":"2024-10-12","cited_by_count":8,"area":null},{"id":"2206.14318","title":"Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2507.22934","title":"Deep Learning Approaches for Multimodal Intent Recognition: A Survey","created":"2025-07-24","cited_by_count":6,"area":null},{"id":"2305.08067","title":"Improving End-to-End SLU performance with Prosodic Attention and Distillation","created":"2023-05-14","cited_by_count":5,"area":null},{"id":"2212.13015","title":"Skit-S2I: An Indian Accented Speech to Intent dataset","created":"2022-12-26","cited_by_count":4,"area":null},{"id":"2404.14415","title":"Domain Adaptation in Intent Classification Systems: A Review","created":"2024-03-26","cited_by_count":4,"area":null},{"id":"2310.00574","title":"YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs","created":"2023-10-01","cited_by_count":1,"area":null},{"id":"2408.02341","title":"An approach to optimize inference of the DIART speaker diarization pipeline","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2410.21091","title":"Large Language Model-assisted Speech and Pointing Benefits Multiple 3D Object Selection in Virtual Reality","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2606.01099","title":"MiCU: End-to-End Smart Home Command Understanding with Large Language Model","created":"2026-05-31","cited_by_count":0,"area":null}],"next_cursor":null}