{"total":21,"rows":[{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148,"area":null},{"id":"2105.00573","title":"Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks","created":"2021-05-02","cited_by_count":24,"area":null},{"id":"2407.11606","title":"The Foundations of Tokenization: Statistical and Computational Concerns","created":"2024-07-16","cited_by_count":22,"area":null},{"id":"2210.07499","title":"Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks","created":"2022-10-14","cited_by_count":13,"area":null},{"id":"2107.11628","title":"Differentiable Allophone Graphs for Language-Universal Speech Recognition","created":"2021-07-24","cited_by_count":10,"area":null},{"id":"2108.00084","title":"The History of Speech Recognition to the Year 2030","created":"2021-07-30","cited_by_count":10,"area":null},{"id":"2201.12208","title":"Star Temporal Classification: Sequence Classification with Partially Labeled Data","created":"2022-01-28","cited_by_count":10,"area":null},{"id":"2306.01031","title":"Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts","created":"2023-06-01","cited_by_count":10,"area":null},{"id":"2303.10384","title":"Powerful and Extensible WFST Framework for RNN-Transducer Losses","created":"2023-03-18","cited_by_count":7,"area":null},{"id":"2308.06547","title":"Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition","created":"2023-08-12","cited_by_count":6,"area":null},{"id":"2111.01272","title":"Sequence Transduction with Graph-based Supervision","created":"2021-11-01","cited_by_count":4,"area":null},{"id":"2203.15614","title":"Integrating Lattice-Free MMI into End-to-End Speech Recognition","created":"2022-03-29","cited_by_count":3,"area":null},{"id":"2312.10087","title":"Revisiting the Entropy Semiring for Neural Speech Recognition","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2203.00232","title":"Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR","created":"2022-03-01","cited_by_count":1,"area":null},{"id":"2410.15575","title":"Neural Search Space in Gboard Decoder","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2504.06963","title":"RNN-Transducer-based Losses for Speech Recognition on Noisy Targets","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2106.00749","title":"Higher-order Derivatives of Weighted Finite-state Machines","created":"2021-06-01","cited_by_count":0,"area":null},{"id":"2110.02848","title":"Parallel Composition of Weighted Finite-State Transducers","created":"2021-10-06","cited_by_count":0,"area":null},{"id":"2304.13134","title":"LAST: Scalable Lattice-Based Speech Modelling in JAX","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2406.18481","title":"Robust Surgical Phase Recognition From Annotation Efficient Supervision","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2609.30160","title":"A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}