{"total":26,"rows":[{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180,"area":null},{"id":"2301.12040","title":"ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts","created":"2023-01-28","cited_by_count":78,"area":null},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71,"area":null},{"id":"2209.15329","title":"SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data","created":"2022-09-30","cited_by_count":49,"area":null},{"id":"2210.03730","title":"SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training","created":"2022-10-07","cited_by_count":40,"area":null},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40,"area":null},{"id":"2104.07253","title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","created":"2021-04-15","cited_by_count":22,"area":null},{"id":"2106.15065","title":"Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding","created":"2021-06-29","cited_by_count":11,"area":null},{"id":"2104.10357","title":"Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning","created":"2021-04-21","cited_by_count":6,"area":null},{"id":"2105.04719","title":"Speech2Slot: An End-to-End Knowledge-based Slot Filling from Speech","created":"2021-05-10","cited_by_count":6,"area":null},{"id":"2106.15919","title":"On joint training with interfaces for spoken language understanding","created":"2021-06-30","cited_by_count":5,"area":null},{"id":"2111.14842","title":"Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?","created":"2021-11-29","cited_by_count":5,"area":null},{"id":"2509.15655","title":"Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2207.00352","title":"Toward Low-Cost End-to-End Spoken Language Understanding","created":"2022-07-01","cited_by_count":3,"area":null},{"id":"2211.08402","title":"Introducing Semantics into Speech Encoders","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2204.05188","title":"Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems","created":"2022-04-11","cited_by_count":2,"area":null},{"id":"2206.14589","title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","created":"2022-06-29","cited_by_count":2,"area":null},{"id":"2211.07710","title":"End-to-End Speech to Intent Prediction to improve E-commerce Customer Support Voicebot in Hindi and English","created":"2022-10-26","cited_by_count":2,"area":null},{"id":"2606.24910","title":"End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2110.09264","title":"Intent Classification Using Pre-trained Language Agnostic Embeddings For Low Resource Languages","created":"2021-10-18","cited_by_count":0,"area":null},{"id":"2211.01263","title":"A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2309.02780","title":"GRASS: Unified Generation Model for Speech-to-Semantic Tasks","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2310.05374","title":"Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2405.15097","title":"Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2502.16584","title":"Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2508.10015","title":"RealTalk-CN: A Realistic Chinese Speech-Text Dialogue Benchmark With Cross-Modal Interaction Analysis","created":"2025-08-06","cited_by_count":0,"area":null}],"next_cursor":null}