{"total":23,"rows":[{"id":"2205.14959","title":"Dataset Condensation via Efficient Synthetic-Data Parameterization","created":"2022-05-30","cited_by_count":188,"area":null},{"id":"2310.11230","title":"Zipformer: A faster and better encoder for automatic speech recognition","created":"2023-10-17","cited_by_count":80,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2206.00888","title":"Squeezeformer: An Efficient Transformer for Automatic Speech Recognition","created":"2022-06-02","cited_by_count":51,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2109.00627","title":"Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition","created":"2021-09-01","cited_by_count":32,"area":null},{"id":"2212.10888","title":"A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability","created":"2022-12-21","cited_by_count":31,"area":null},{"id":"2304.14535","title":"Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization","created":"2023-04-27","cited_by_count":28,"area":null},{"id":"2110.00478","title":"SECDA: Efficient Hardware/Software Co-Design of FPGA-based DNN Accelerators for Edge Inference","created":"2021-10-01","cited_by_count":12,"area":null},{"id":"2205.09058","title":"Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator","created":"2022-05-18","cited_by_count":11,"area":null},{"id":"2312.04234","title":"Graph Convolutions Enrich the Self-Attention in Transformers!","created":"2023-12-07","cited_by_count":11,"area":null},{"id":"2102.07259","title":"Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2301.12528","title":"Sequential Estimation of Gaussian Process-based Deep State-Space Models","created":"2023-01-29","cited_by_count":5,"area":null},{"id":"2503.23542","title":"Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2110.02375","title":"Interpreting intermediate convolutional layers in unsupervised acoustic word classification","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2207.08179","title":"End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting","created":"2022-07-17","cited_by_count":3,"area":null},{"id":"2305.07034","title":"Quran Recitation Recognition using End-to-End Deep Learning","created":"2023-05-10","cited_by_count":3,"area":null},{"id":"2403.00854","title":"Speaker-Independent Dysarthria Severity Classification using Self-Supervised Transformers and Multi-Task Learning","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2102.02326","title":"Effects of Number of Filters of Convolutional Layers on Speech Recognition Model Accuracy","created":"2021-02-03","cited_by_count":1,"area":null},{"id":"2105.09742","title":"Robustness of end-to-end Automatic Speech Recognition Models -- A Case Study using Mozilla DeepSpeech","created":"2021-05-08","cited_by_count":0,"area":null},{"id":"2108.03818","title":"Time-Frequency Localization Using Deep Convolutional Maxout Neural Network in Persian Speech Recognition","created":"2021-08-09","cited_by_count":0,"area":null},{"id":"2509.23550","title":"Automatic Speech Recognition for Greek Medical Dictation","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2510.04044","title":"Quantization Range Estimation for Convolutional Neural Networks","created":"2025-10-05","cited_by_count":0,"area":null}],"next_cursor":null}