{"total":108,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516,"area":"lr"},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469,"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":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2412.08821","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","created":"2024-12-11","cited_by_count":89,"area":null},{"id":"2204.03409","title":"MAESTRO: Matched Speech Text Representations through Modality Matching","created":"2022-04-07","cited_by_count":79,"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":"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":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"area":null},{"id":"2209.11379","title":"Do Current Multi-Task Optimization Methods in Deep Learning Even Help?","created":"2022-09-23","cited_by_count":60,"area":null},{"id":"2212.08055","title":"UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units","created":"2022-12-15","cited_by_count":60,"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":"2212.09660","title":"The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2305.01778","title":"SLTUNET: A Simple Unified Model for Sign Language Translation","created":"2023-05-02","cited_by_count":35,"area":null},{"id":"2205.08180","title":"SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation","created":"2022-05-17","cited_by_count":32,"area":null},{"id":"2302.12829","title":"Improving Massively Multilingual ASR With Auxiliary CTC Objectives","created":"2023-02-24","cited_by_count":31,"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":"2301.11716","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","created":"2023-01-27","cited_by_count":25,"area":null},{"id":"2501.17202","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","created":"2025-01-27","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":"2203.10752","title":"XTREME-S: Evaluating Cross-lingual Speech Representations","created":"2022-03-21","cited_by_count":22,"area":null},{"id":"2203.13339","title":"Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation","created":"2022-03-24","cited_by_count":20,"area":null},{"id":"2305.12606","title":"Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages","created":"2023-05-21","cited_by_count":20,"area":null},{"id":"2211.00115","title":"Textless Direct Speech-to-Speech Translation with Discrete Speech Representation","created":"2022-10-31","cited_by_count":19,"area":null},{"id":"2205.12216","title":"T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation","created":"2022-05-24","cited_by_count":16,"area":null},{"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":"2211.01458","title":"Towards Zero-Shot Code-Switched Speech Recognition","created":"2022-11-02","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":"2306.11646","title":"Recent Advances in Direct Speech-to-text Translation","created":"2023-06-20","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":"2305.17547","title":"Translatotron 3: Speech to Speech Translation with Monolingual Data","created":"2023-05-27","cited_by_count":12,"area":null},{"id":"2308.01831","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","created":"2023-08-03","cited_by_count":11,"area":null},{"id":"2210.06324","title":"SQuId: Measuring Speech Naturalness in Many Languages","created":"2022-10-12","cited_by_count":10,"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":"2210.17027","title":"Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation","created":"2022-10-31","cited_by_count":9,"area":null},{"id":"2212.00500","title":"MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition","created":"2022-11-29","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":"2306.08374","title":"SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?","created":"2023-06-14","cited_by_count":9,"area":null},{"id":"2409.03701","title":"LAST: Language Model Aware Speech Tokenization","created":"2024-09-05","cited_by_count":9,"area":null},{"id":"2212.09553","title":"Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models","created":"2022-12-19","cited_by_count":7,"area":null},{"id":"2312.06134","title":"Order Matters in the Presence of Dataset Imbalance for Multilingual Learning","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2512.16378","title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","created":"2025-12-18","cited_by_count":7,"area":null},{"id":"2210.09556","title":"Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2304.14514","title":"Understanding Shared Speech-Text Representations","created":"2023-04-27","cited_by_count":6,"area":null},{"id":"2509.12093","title":"SENSE models: an open source solution for multilingual and multimodal semantic-based tasks","created":"2025-09-15","cited_by_count":6,"area":null},{"id":"2209.02982","title":"Improving the Cross-Lingual Generalisation in Visual Question Answering","created":"2022-09-07","cited_by_count":5,"area":"mllm"},{"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":"2404.01616","title":"Transforming LLMs into Cross-modal and Cross-lingual Retrieval Systems","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2411.04699","title":"Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages","created":"2024-11-07","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":"2401.08992","title":"Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR","created":"2024-01-17","cited_by_count":4,"area":null},{"id":"2405.14259","title":"Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR","created":"2024-05-23","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":"2409.13523","title":"EMMeTT: Efficient Multimodal Machine Translation Training","created":"2024-09-20","cited_by_count":4,"area":null},{"id":"2210.12562","title":"Greedy Modality Selection via Approximate Submodular Maximization","created":"2022-10-22","cited_by_count":3,"area":null},{"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":"2211.03025","title":"Bridging Speech and Textual Pre-trained Models with Unsupervised ASR","created":"2022-11-06","cited_by_count":3,"area":null},{"id":"2303.03600","title":"Adaptive Knowledge Distillation between Text and Speech Pre-trained Models","created":"2023-03-07","cited_by_count":3,"area":"distill"},{"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":"2506.03681","title":"Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering","created":"2025-06-04","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":"2211.11703","title":"Towards continually learning new languages","created":"2022-11-21","cited_by_count":2,"area":null},{"id":"2305.19759","title":"Simple yet Effective Code-Switching Language Identification with Multitask Pre-Training and Transfer Learning","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2306.00789","title":"Improved Cross-Lingual Transfer Learning For Automatic Speech Translation","created":"2023-06-01","cited_by_count":2,"area":"distill"},{"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":"2311.00697","title":"End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2311.15954","title":"A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2312.07338","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","created":"2023-12-12","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":"2412.02805","title":"STORM: Strategic Orchestration of Modalities for Rare Event Classification","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2602.03868","title":"Benchmarking Automatic Speech Recognition for Indian Languages in Agricultural Contexts","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.22039","title":"TG-ASR: Translation-Guided Learning with Parallel Gated Cross Attention for Low-Resource Automatic Speech Recognition","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2302.10871","title":"Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation","created":"2023-02-21","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":"2503.00957","title":"Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks","created":"2025-03-02","cited_by_count":1,"area":null},{"id":"2506.06343","title":"TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2309.07478","title":"Direct Text to Speech Translation System using Acoustic Units","created":"2023-09-14","cited_by_count":0,"area":null},{"id":"2309.09443","title":"Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter","created":"2023-09-18","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":"2311.08141","title":"GMTR: Graph Matching Transformers","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2312.16805","title":"DarkShot: Lighting Dark Images with Low-Compute and High-Quality","created":"2023-12-28","cited_by_count":0,"area":null},{"id":"2401.05431","title":"TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2401.05432","title":"TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2401.12471","title":"Training-Free Action Recognition and Goal Inference with Dynamic Frame Selection","created":"2024-01-23","cited_by_count":0,"area":null},{"id":"2403.13663","title":"T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2408.17101","title":"Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2410.11162","title":"Towards General Deepfake Detection with Dynamic Curriculum","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2410.13409","title":"Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphs","created":"2024-10-17","cited_by_count":0,"area":null}],"next_cursor":"100"}