{"total":21,"rows":[{"id":"2509.09987","title":"Whisper Has an Internal Word Aligner","created":"2025-09-12","cited_by_count":7,"area":null},{"id":"2506.14177","title":"Can we train ASR systems on Code-switch without real code-switch data? Case study for Singapore's languages","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2606.18466","title":"Montreal Forced Aligner and the state of speech-to-text alignment in 2026","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2607.18934","title":"Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing","created":"2026-07-21","cited_by_count":3,"area":null},{"id":"2501.19010","title":"DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2512.17915","title":"Supplementary Resources and Analysis for Automatic Speech Recognition Systems Trained on the Loquacious Dataset","created":"2025-11-27","cited_by_count":2,"area":null},{"id":"2601.18617","title":"Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networks","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2508.07229","title":"How Does a Deep Neural Network Look at Lexical Stress in English Words?","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2606.10675","title":"Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.25460","title":"Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.05365","title":"SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.06831","title":"Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2608.28508","title":"Phoneme- and Word-Level Metrics Using Self-Supervised Speech Representations for Forced Alignment Evaluation","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2606.28857","title":"wav2VOT: Automatic estimation of voice onset time, closure duration, and burst realisation with wav2vec2","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.13158","title":"Do LLMs Need Architectural Changes for Simultaneous Speech Translation? A Prefix-to-Prefix Data Driven Approach","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.21332","title":"Phonetic forced alignment for low-resource language varieties: Model training and evaluation on Chengdu Mandarin","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.25581","title":"Evaluation of forced alignment of code-mixed speech: the case of Hindi-English","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.24041","title":"Relative Time Intervals Representation for Word-level Timestamping with Masked Training","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.32396","title":"FA-Bench: A Benchmark for Phone- and Word-Level Timestamp Accuracy in Forced Alignment and ASR on Clean and Noisy Speech","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33650","title":"FuseAlign: Forced Alignment in the Wild","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.17782","title":"Where Words Begin and End","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}