{"total":19,"rows":[{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2210.07353","title":"JOIST: A Joint Speech and Text Streaming Model For ASR","created":"2022-10-13","cited_by_count":24,"area":null},{"id":"2302.08917","title":"Massively Multilingual Shallow Fusion with Large Language Models","created":"2023-02-17","cited_by_count":10,"area":null},{"id":"2302.08583","title":"JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition","created":"2023-02-16","cited_by_count":9,"area":null},{"id":"2305.18096","title":"Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target","created":"2023-05-29","cited_by_count":6,"area":null},{"id":"2509.15389","title":"Exploring Fine-Tuning of Large Audio Language Models for Spoken Language Understanding under Limited Speech Data","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2305.12793","title":"Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2306.04076","title":"Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2308.06125","title":"Improving Joint Speech-Text Representations Without Alignment","created":"2023-08-11","cited_by_count":4,"area":null},{"id":"2412.06967","title":"Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuning","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2406.02921","title":"Text Injection for Neural Contextual Biasing","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2401.07575","title":"Cascaded Cross-Modal Transformer for Audio-Textual Classification","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2406.06664","title":"ASTRA: Aligning Speech and Text Representations for Asr without Sampling","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2312.01842","title":"Exploring the Viability of Synthetic Audio Data for Audio-Based Dialogue State Tracking","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2511.22503","title":"Joint Speech and Text Training for LLM-Based End-to-End Spoken Dialogue State Tracking","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2308.08027","title":"End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations","created":"2023-08-15","cited_by_count":0,"area":null},{"id":"2309.02459","title":"Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2407.04601","title":"Written Term Detection Improves Spoken Term Detection","created":"2024-07-05","cited_by_count":0,"area":null},{"id":"2604.26514","title":"Text-Utilization for Encoder-dominated Speech Recognition Models","created":"2026-04-29","cited_by_count":0,"area":null}],"next_cursor":null}