{"total":25,"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":"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":"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":"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":"2310.05224","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","created":"2023-10-08","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":"2206.11332","title":"DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon","created":"2022-06-22","cited_by_count":12,"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":"2109.10179","title":"How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings","created":"2021-09-21","cited_by_count":8,"area":null},{"id":"2204.05148","title":"Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning","created":"2022-04-11","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":"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":"2206.13231","title":"QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixer","created":"2022-06-23","cited_by_count":4,"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":"2301.03012","title":"Analyzing the Representational Geometry of Acoustic Word Embeddings","created":"2023-01-08","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":"2210.12857","title":"Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings","created":"2022-10-23","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":"2310.05235","title":"XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words","created":"2023-10-08","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":"2211.01089","title":"Transformer-based encoder-encoder architecture for Spoken Term Detection","created":"2022-11-02","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":"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}],"next_cursor":null}