{"total":19,"rows":[{"id":"2102.07594","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","created":"2021-02-15","cited_by_count":31,"area":null},{"id":"2102.07061","title":"Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Loss","created":"2021-02-14","cited_by_count":25,"area":null},{"id":"2103.10731","title":"Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation","created":"2021-03-19","cited_by_count":19,"area":null},{"id":"2303.05309","title":"MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2110.15957","title":"Visual Keyword Spotting with Attention","created":"2021-10-29","cited_by_count":11,"area":null},{"id":"2106.12834","title":"Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language","created":"2021-06-24","cited_by_count":7,"area":null},{"id":"2108.10357","title":"End-to-End Open Vocabulary Keyword Search","created":"2021-08-23","cited_by_count":6,"area":null},{"id":"2201.01209","title":"Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Question","created":"2022-01-04","cited_by_count":6,"area":null},{"id":"2106.04897","title":"Unsupervised Automatic Speech Recognition: A Review","created":"2021-06-09","cited_by_count":5,"area":null},{"id":"2306.00410","title":"Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2110.14594","title":"End-to-end LSTM based estimation of volcano event epicenter localization","created":"2021-10-27","cited_by_count":2,"area":null},{"id":"2211.06478","title":"Exploring Sequence-to-Sequence Transformer-Transducer Models for Keyword Spotting","created":"2022-11-11","cited_by_count":2,"area":null},{"id":"2305.17706","title":"Spot keywords from very noisy and mixed speech","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2405.14489","title":"End-to-End User-Defined Keyword Spotting using Shifted Delta Coefficients","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2407.04652","title":"Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2211.08790","title":"Structural Segmentation and Labeling of Tabla Solo Performances","created":"2022-11-16","cited_by_count":0,"area":null},{"id":"2308.08027","title":"End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations","created":"2023-08-15","cited_by_count":0,"area":null},{"id":"2401.04235","title":"High-precision Voice Search Query Correction via Retrievable Speech-text Embedings","created":"2024-01-08","cited_by_count":0,"area":null},{"id":"2407.04601","title":"Written Term Detection Improves Spoken Term Detection","created":"2024-07-05","cited_by_count":0,"area":null}],"next_cursor":null}