{"total":22,"rows":[{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2210.16043","title":"Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models","created":"2022-10-28","cited_by_count":21,"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":"2106.08859","title":"Attention-Based Keyword Localisation in Speech using Visual Grounding","created":"2021-06-16","cited_by_count":13,"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":"2202.01107","title":"Keyword localisation in untranscribed speech using visually grounded speech models","created":"2022-02-02","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":"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":"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":"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":"2210.12857","title":"Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings","created":"2022-10-23","cited_by_count":2,"area":null},{"id":"2306.02153","title":"Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling","created":"2023-06-03","cited_by_count":2,"area":null},{"id":"2307.02083","title":"Leveraging multilingual transfer for unsupervised semantic acoustic word embeddings","created":"2023-07-05","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":"2106.06160","title":"Spoken Term Detection Methods for Sparse Transcription in Very Low-resource Settings","created":"2021-06-11","cited_by_count":0,"area":null},{"id":"2112.01757","title":"BBS-KWS:The Mandarin Keyword Spotting System Won the Video Keyword Wakeup Challenge","created":"2021-12-03","cited_by_count":0,"area":null},{"id":"2410.04091","title":"Cross-Lingual Query-by-Example Spoken Term Detection: A Transformer-Based Approach","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2501.11631","title":"Noise-Agnostic Multitask Whisper Training for Reducing False Alarm Errors in Call-for-Help Detection","created":"2025-01-20","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":"2603.18023","title":"PCOV-KWS: Multi-task Learning for Personalized Customizable Open Vocabulary Keyword Spotting","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.18024","title":"ProKWS: Personalized Keyword Spotting via Collaborative Learning of Phonemes and Prosody","created":"2026-03-05","cited_by_count":0,"area":null}],"next_cursor":null}