{"total":47,"rows":[{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2403.16973","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","created":"2024-03-25","cited_by_count":120,"area":null},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2203.15081","title":"Word Discovery in Visually Grounded, Self-Supervised Speech Models","created":"2022-03-28","cited_by_count":37,"area":null},{"id":"2205.12523","title":"TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation","created":"2022-05-25","cited_by_count":34,"area":null},{"id":"2104.13225","title":"Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques","created":"2021-04-27","cited_by_count":32,"area":null},{"id":"2210.00705","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","created":"2022-10-03","cited_by_count":29,"area":null},{"id":"2203.15863","title":"WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models","created":"2022-03-29","cited_by_count":26,"area":null},{"id":"2202.03543","title":"Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling","created":"2022-02-07","cited_by_count":25,"area":null},{"id":"2109.06912","title":"fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit","created":"2021-09-14","cited_by_count":24,"area":null},{"id":"2109.08186","title":"Fast-Slow Transformer for Visually Grounding Speech","created":"2021-09-16","cited_by_count":23,"area":null},{"id":"2305.18957","title":"Wave to Syntax: Probing spoken language models for syntax","created":"2023-05-30","cited_by_count":18,"area":null},{"id":"2203.15796","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition","created":"2022-03-29","cited_by_count":14,"area":null},{"id":"2110.03342","title":"VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over","created":"2021-10-07","cited_by_count":13,"area":null},{"id":"2109.14200","title":"Can phones, syllables, and words emerge as side-products of cross-situational audiovisual learning? -- A computational investigation","created":"2021-09-29","cited_by_count":12,"area":null},{"id":"2305.11435","title":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model","created":"2023-05-19","cited_by_count":11,"area":null},{"id":"2211.01180","title":"M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval","created":"2022-11-02","cited_by_count":9,"area":null},{"id":"2207.11964","title":"ConceptBeam: Concept Driven Target Speech Extraction","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2107.06546","title":"ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition","created":"2021-07-14","cited_by_count":6,"area":null},{"id":"2106.08648","title":"Semantic sentence similarity: size does not always matter","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2209.00277","title":"Video-Guided Curriculum Learning for Spoken Video Grounding","created":"2022-09-01","cited_by_count":5,"area":null},{"id":"2402.16021","title":"TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages","created":"2024-02-25","cited_by_count":5,"area":null},{"id":"2306.11371","title":"Visually grounded few-shot word learning in low-resource settings","created":"2023-06-20","cited_by_count":4,"area":null},{"id":"2406.04906","title":"RU-AI: A Large Multimodal Dataset for Machine-Generated Content Detection","created":"2024-06-07","cited_by_count":4,"area":null},{"id":"2409.18372","title":"You Only Speak Once to See","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2406.05259","title":"A model of early word acquisition based on realistic-scale audiovisual naming events","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2409.12306","title":"Measuring Sound Symbolism in Audio-visual Models","created":"2024-09-18","cited_by_count":3,"area":null},{"id":"2110.07575","title":"Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2302.00765","title":"Visually Grounded Keyword Detection and Localisation for Low-Resource Languages","created":"2023-02-01","cited_by_count":2,"area":null},{"id":"2303.08809","title":"Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2306.02972","title":"Simultaneous or Sequential Training? How Speech Representations Cooperate in a Multi-Task Self-Supervised Learning System","created":"2023-06-05","cited_by_count":2,"area":null},{"id":"2310.07654","title":"Audio-Visual Neural Syntax Acquisition","created":"2023-10-11","cited_by_count":2,"area":null},{"id":"2410.00822","title":"VHASR: A Multimodal Speech Recognition System With Vision Hotwords","created":"2024-10-01","cited_by_count":2,"area":null},{"id":"2510.03639","title":"Towards Unsupervised Speech Recognition at the Syllable-Level","created":"2025-10-04","cited_by_count":2,"area":null},{"id":"2211.08983","title":"Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates","created":"2022-11-14","cited_by_count":1,"area":null},{"id":"2305.15937","title":"Visually grounded few-shot word acquisition with fewer shots","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2402.05819","title":"Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2408.13119","title":"Coarse-to-fine Alignment Makes Better Speech-image Retrieval","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2509.15837","title":"The Curious Case of Visual Grounding: Different Effects for Speech- and Text-based Language Encoders","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2407.14212","title":"Braille-to-Speech Generator: Audio Generation Based on Joint Fine-Tuning of CLIP and Fastspeech2","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2408.04723","title":"Survey: Transformer-based Models in Data Modality Conversion","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2408.13705","title":"Cross-Modal Denoising: A Novel Training Paradigm for Enhancing Speech-Image Retrieval","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2410.03739","title":"Grammar Induction from Visual, Speech and Text","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2511.03423","title":"Seeing What You Say: Expressive Image Generation from Speech","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2610.13298","title":"Multi-Source and Multi-Dimensional Information Fusion in Resource-Constrained Edge Networks","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}