{"total":79,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411,"area":null},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343,"area":null},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231,"area":null},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2310.09424","title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","created":"2023-10-13","cited_by_count":76,"area":null},{"id":"2309.07937","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","created":"2023-09-14","cited_by_count":72,"area":null},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"area":null},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68,"area":null},{"id":"2310.00230","title":"SLM: Bridge the thin gap between speech and text foundation models","created":"2023-09-30","cited_by_count":67,"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":"2211.11275","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","created":"2022-11-21","cited_by_count":37,"area":null},{"id":"2310.08715","title":"Toward Joint Language Modeling for Speech Units and Text","created":"2023-10-12","cited_by_count":28,"area":null},{"id":"2302.06419","title":"AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","created":"2023-02-10","cited_by_count":27,"area":null},{"id":"2301.11716","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","created":"2023-01-27","cited_by_count":25,"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":"2305.14635","title":"CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation","created":"2023-05-24","cited_by_count":22,"area":null},{"id":"2402.01828","title":"Retrieval Augmented End-to-End Spoken Dialog Models","created":"2024-02-02","cited_by_count":20,"area":"rag"},{"id":"2212.08486","title":"BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric","created":"2022-12-16","cited_by_count":16,"area":null},{"id":"2210.15447","title":"Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech","created":"2022-10-27","cited_by_count":15,"area":null},{"id":"2305.08706","title":"Understanding and Bridging the Modality Gap for Speech Translation","created":"2023-05-15","cited_by_count":15,"area":null},{"id":"2210.10027","title":"Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2302.01496","title":"Efficient Domain Adaptation for Speech Foundation Models","created":"2023-02-03","cited_by_count":13,"area":null},{"id":"2302.14036","title":"Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator","created":"2023-02-27","cited_by_count":11,"area":null},{"id":"2303.10949","title":"Code-Switching Text Generation and Injection in Mandarin-English ASR","created":"2023-03-20","cited_by_count":11,"area":null},{"id":"2211.02809","title":"LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2212.08704","title":"Speech Aware Dialog System Technology Challenge (DSTC11)","created":"2022-12-16","cited_by_count":10,"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":"2305.08709","title":"Back Translation for Speech-to-text Translation Without Transcripts","created":"2023-05-15","cited_by_count":9,"area":null},{"id":"2305.14838","title":"ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2306.07944","title":"Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2304.14514","title":"Understanding Shared Speech-Text Representations","created":"2023-04-27","cited_by_count":6,"area":null},{"id":"2311.08966","title":"Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducer","created":"2023-11-15","cited_by_count":6,"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":"2503.00733","title":"UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation","created":"2025-03-02","cited_by_count":5,"area":null},{"id":"2211.00325","title":"Speech-text based multi-modal training with bidirectional attention for improved speech recognition","created":"2022-11-01","cited_by_count":4,"area":null},{"id":"2305.09210","title":"Towards Speech Dialogue Translation Mediating Speakers of Different Languages","created":"2023-05-16","cited_by_count":4,"area":null},{"id":"2308.06125","title":"Improving Joint Speech-Text Representations Without Alignment","created":"2023-08-11","cited_by_count":4,"area":null},{"id":"2406.10993","title":"CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving","created":"2024-06-16","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":"2506.08633","title":"Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2512.02593","title":"Spoken Conversational Agents with Large Language Models","created":"2025-12-02","cited_by_count":4,"area":"agents"},{"id":"2210.16755","title":"token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text","created":"2022-10-30","cited_by_count":3,"area":null},{"id":"2212.03232","title":"Learning the joint distribution of two sequences using little or no paired data","created":"2022-12-06","cited_by_count":3,"area":null},{"id":"2305.17000","title":"DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2308.07393","title":"Using Text Injection to Improve Recognition of Personal Identifiers in Speech","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2309.15826","title":"Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing","created":"2023-09-27","cited_by_count":3,"area":null},{"id":"2310.20456","title":"Towards a Deep Understanding of Multilingual End-to-End Speech Translation","created":"2023-10-31","cited_by_count":3,"area":null},{"id":"2406.02921","title":"Text Injection for Neural Contextual Biasing","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2411.07607","title":"CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR","created":"2024-11-12","cited_by_count":3,"area":null},{"id":"2209.06418","title":"Graph Perceiver IO: A General Architecture for Graph Structured Data","created":"2022-09-14","cited_by_count":2,"area":null},{"id":"2305.07677","title":"Masked Audio Text Encoders are Effective Multi-Modal Rescorers","created":"2023-05-11","cited_by_count":2,"area":null},{"id":"2309.09390","title":"Augmenting text for spoken language understanding with Large Language Models","created":"2023-09-17","cited_by_count":2,"area":null},{"id":"2310.03724","title":"Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer","created":"2023-10-05","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":"2406.09950","title":"An efficient text augmentation approach for contextualized Mandarin speech recognition","created":"2024-06-14","cited_by_count":2,"area":null},{"id":"2407.16840","title":"Synth4Kws: Synthesized Speech for User Defined Keyword Spotting in Low Resource Environments","created":"2024-07-23","cited_by_count":2,"area":null},{"id":"2412.13071","title":"CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information Retrieval","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2308.07395","title":"Text Injection for Capitalization and Turn-Taking Prediction in Speech Models","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2310.05919","title":"Few-Shot Spoken Language Understanding via Joint Speech-Text Models","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2406.08380","title":"Towards Unsupervised Speech Recognition Without Pronunciation Models","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2410.05146","title":"CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2506.19159","title":"Enhanced Hybrid Transducer and Attention Encoder Decoder with Text Data","created":"2025-06-23","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":"2309.10567","title":"Multimodal Modeling For Spoken Language Identification","created":"2023-09-19","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":"2310.06702","title":"Temporally Aligning Long Audio Interviews with Questions: A Case Study in Multimodal Data Integration","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2401.04235","title":"High-precision Voice Search Query Correction via Retrievable Speech-text Embedings","created":"2024-01-08","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":"2411.18368","title":"AMPS: ASR with Multimodal Paraphrase Supervision","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2508.11189","title":"Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation","created":"2025-08-15","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},{"id":"2607.01733","title":"Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving","created":"2026-07-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}