{"total":19,"rows":[{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"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":"2306.05245","title":"Matching Latent Encoding for Audio-Text based Keyword Spotting","created":"2023-06-08","cited_by_count":15,"area":null},{"id":"2106.08686","title":"Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Study","created":"2021-06-16","cited_by_count":8,"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":"2103.05468","title":"CNN-based Spoken Term Detection and Localization without Dynamic Programming","created":"2021-03-07","cited_by_count":6,"area":null},{"id":"2210.11895","title":"Spoken Term Detection and Relevance Score Estimation using Dot-Product of Pronunciation Embeddings","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2210.14564","title":"AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2403.08738","title":"Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representations","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2406.05314","title":"Relational Proxy Loss for Audio-Text based Keyword Spotting","created":"2024-06-08","cited_by_count":3,"area":null},{"id":"2209.06633","title":"Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings","created":"2022-09-14","cited_by_count":2,"area":null},{"id":"2412.18142","title":"Text-Aware Adapter for Few-Shot Keyword Spotting","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2207.14568","title":"Learning Phone Recognition from Unpaired Audio and Phone Sequences Based on Generative Adversarial Network","created":"2022-07-29","cited_by_count":1,"area":null},{"id":"2505.16735","title":"Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2306.11473","title":"Timestamped Embedding-Matching Acoustic-to-Word CTC ASR","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2308.00129","title":"Speech representation learning: Learning bidirectional encoders with single-view, multi-view, and multi-task methods","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2406.07923","title":"CTC-aligned Audio-Text Embedding for Streaming Open-vocabulary Keyword Spotting","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2512.14115","title":"Joint Multimodal Contrastive Learning for Robust Spoken Term Detection and Keyword Spotting","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2601.14012","title":"MATE: Matryoshka Audio-Text Embeddings for Open-Vocabulary Keyword Spotting","created":"2026-01-20","cited_by_count":0,"area":null}],"next_cursor":null}