{"total":18,"rows":[{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419,"area":null},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130,"area":null},{"id":"2102.01547","title":"WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit","created":"2021-02-02","cited_by_count":125,"area":null},{"id":"2203.15455","title":"WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit","created":"2022-03-29","cited_by_count":47,"area":null},{"id":"2101.05014","title":"Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks","created":"2021-01-13","cited_by_count":8,"area":null},{"id":"2202.07855","title":"Conversational Speech Recognition By Learning Conversation-level Characteristics","created":"2022-02-16","cited_by_count":8,"area":null},{"id":"2108.01129","title":"Decoupling recognition and transcription in Mandarin ASR","created":"2021-08-02","cited_by_count":6,"area":null},{"id":"2107.03069","title":"Efficient Transformer for Direct Speech Translation","created":"2021-07-07","cited_by_count":5,"area":null},{"id":"2408.04905","title":"GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models","created":"2024-08-09","cited_by_count":5,"area":null},{"id":"2510.04008","title":"RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts","created":"2025-10-05","cited_by_count":5,"area":null},{"id":"2207.00883","title":"Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanism","created":"2022-07-02","cited_by_count":4,"area":null},{"id":"2203.10252","title":"Similarity and Content-based Phonetic Self Attention for Speech Recognition","created":"2022-03-19","cited_by_count":3,"area":null},{"id":"2301.12444","title":"Exploring Attention Map Reuse for Efficient Transformer Neural Networks","created":"2023-01-29","cited_by_count":3,"area":null},{"id":"2207.14578","title":"Pronunciation-aware unique character encoding for RNN Transducer-based Mandarin speech recognition","created":"2022-07-29","cited_by_count":1,"area":null},{"id":"2501.09309","title":"Understanding Mental Health Content on Social Media and Its Effect Towards Suicidal Ideation","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2108.08207","title":"SHAQ: Single Headed Attention with Quasi-Recurrence","created":"2021-08-18","cited_by_count":0,"area":null},{"id":"2309.01437","title":"SememeASR: Boosting Performance of End-to-End Speech Recognition against Domain and Long-Tailed Data Shift with Sememe Semantic Knowledge","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2411.03375","title":"Kernel Approximation using Analog In-Memory Computing","created":"2024-11-05","cited_by_count":0,"area":null}],"next_cursor":null}