{"total":19,"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":"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":"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":"2106.09009","title":"End-to-End Spoken Language Understanding for Generalized Voice Assistants","created":"2021-06-16","cited_by_count":17,"area":null},{"id":"2305.11579","title":"Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment","created":"2023-05-19","cited_by_count":13,"area":null},{"id":"2109.02823","title":"Learning Visual-Audio Representations for Voice-Controlled Robots","created":"2021-09-07","cited_by_count":5,"area":null},{"id":"2204.00558","title":"Multi-task RNN-T with Semantic Decoder for Streamable Spoken Language Understanding","created":"2022-04-01","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":"2307.11005","title":"Integrating Pretrained ASR and LM to Perform Sequence Generation for Spoken Language Understanding","created":"2023-07-20","cited_by_count":2,"area":null},{"id":"2205.11008","title":"Calibrate and Refine! A Novel and Agile Framework for ASR-error Robust Intent Detection","created":"2022-05-23","cited_by_count":1,"area":null},{"id":"2203.12067","title":"Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis","created":"2022-03-22","cited_by_count":0,"area":null},{"id":"2204.09227","title":"Cross-stitched Multi-modal Encoders","created":"2022-04-20","cited_by_count":0,"area":null},{"id":"2211.14320","title":"Bidirectional Representations for Low Resource Spoken Language Understanding","created":"2022-11-24","cited_by_count":0,"area":null},{"id":"2305.02937","title":"End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders","created":"2023-05-04","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":"2402.01298","title":"Learning Semantic Information from Raw Audio Signal Using Both Contextual and Phonetic Representations","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2606.01099","title":"MiCU: End-to-End Smart Home Command Understanding with Large Language Model","created":"2026-05-31","cited_by_count":0,"area":null}],"next_cursor":null}