{"list":"other","total":87,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"2101.00390","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","created":"2021-01-02","cited_by_count":463},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411},{"id":"2106.06909","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","created":"2021-06-13","cited_by_count":399},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388},{"id":"1709.05522","title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","created":"2017-09-16","cited_by_count":373},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2302.09210","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","created":"2023-02-18","cited_by_count":348},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"1811.03115","title":"Blockwise Parallel Decoding for Deep Autoregressive Models","created":"2018-11-07","cited_by_count":323},{"id":"2401.07851","title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding","created":"2024-01-15","cited_by_count":269},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"1805.04699","title":"TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation","created":"2018-05-12","cited_by_count":226},{"id":"1704.01279","title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","created":"2017-04-05","cited_by_count":225},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178},{"id":"2005.11262","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","created":"2020-05-22","cited_by_count":155},{"id":"2307.03917","title":"On decoder-only architecture for speech-to-text and large language model integration","created":"2023-07-08","cited_by_count":145},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"1808.10583","title":"AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale","created":"2018-08-31","cited_by_count":128},{"id":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128},{"id":"2308.09936","title":"BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions","created":"2023-08-19","cited_by_count":125},{"id":"2305.10427","title":"Accelerating Transformer Inference for Translation via Parallel Decoding","created":"2023-05-17","cited_by_count":124},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123},{"id":"1911.03167","title":"Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates","created":"2019-11-08","cited_by_count":114},{"id":"2112.01716","title":"Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research","created":"2021-12-03","cited_by_count":102},{"id":"2102.01757","title":"The Multilingual TEDx Corpus for Speech Recognition and Translation","created":"2021-02-02","cited_by_count":101},{"id":"2305.11013","title":"FunASR: A Fundamental End-to-End Speech Recognition Toolkit","created":"2023-05-18","cited_by_count":95},{"id":"2402.02680","title":"Large Language Models are Geographically Biased","created":"2024-02-05","cited_by_count":93},{"id":"2112.02706","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","created":"2021-12-05","cited_by_count":91},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85},{"id":"2104.02133","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","created":"2021-04-05","cited_by_count":83},{"id":"2011.02048","title":"SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation","created":"2020-11-03","cited_by_count":81},{"id":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80},{"id":"2004.06358","title":"Speech Translation and the End-to-End Promise: Taking Stock of Where We Are","created":"2020-04-14","cited_by_count":77},{"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},{"id":"2106.15195","title":"Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers","created":"2021-06-29","cited_by_count":71},{"id":"2310.00230","title":"SLM: Bridge the thin gap between speech and text foundation models","created":"2023-09-30","cited_by_count":67},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66},{"id":"1611.09827","title":"Learning Features of Music from Scratch","created":"2016-11-29","cited_by_count":58},{"id":"2308.15930","title":"LLaSM: Large Language and Speech Model","created":"2023-08-30","cited_by_count":58},{"id":"2310.06434","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","created":"2023-10-10","cited_by_count":56},{"id":"2106.01045","title":"Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?","created":"2021-06-02","cited_by_count":54},{"id":"2102.01578","title":"CTC-based Compression for Direct Speech Translation","created":"2021-02-02","cited_by_count":45},{"id":"2305.11095","title":"Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization","created":"2023-05-18","cited_by_count":43},{"id":"2402.05406","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","created":"2024-02-08","cited_by_count":43},{"id":"2308.12792","title":"Sparks of Large Audio Models: A Survey and Outlook","created":"2023-08-24","cited_by_count":41},{"id":"2309.07081","title":"Can Whisper perform speech-based in-context learning?","created":"2023-09-13","cited_by_count":35},{"id":"2211.02289","title":"CochlScene: Acquisition of acoustic scene data using crowdsourcing","created":"2022-11-04","cited_by_count":33},{"id":"2105.15179","title":"How transfer learning impacts linguistic knowledge in deep NLP models?","created":"2021-05-31","cited_by_count":32},{"id":"2311.02248","title":"COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning","created":"2023-11-03","cited_by_count":31},{"id":"2305.16806","title":"Do GPTs Produce Less Literal Translations?","created":"2023-05-26","cited_by_count":30},{"id":"2303.12642","title":"Democratising AI: Multiple Meanings, Goals, and Methods","created":"2023-03-22","cited_by_count":29},{"id":"2312.13585","title":"Speech Translation with Large Language Models: An Industrial Practice","created":"2023-12-21","cited_by_count":28},{"id":"2203.15863","title":"WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models","created":"2022-03-29","cited_by_count":26},{"id":"2204.03783","title":"Does Simultaneous Speech Translation need Simultaneous Models?","created":"2022-04-08","cited_by_count":22},{"id":"2204.03939","title":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus","created":"2022-04-08","cited_by_count":20},{"id":"2202.07894","title":"Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers","created":"2022-02-16","cited_by_count":19},{"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},{"id":"2310.02050","title":"Tuning Large language model for End-to-end Speech Translation","created":"2023-10-03","cited_by_count":9},{"id":"2402.00632","title":"Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases","created":"2024-02-01","cited_by_count":5}],"next_cursor":null}