{"list":"other","total":77,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"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":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"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":"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":"2304.01933","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2023-04-04","cited_by_count":324},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"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":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"1902.10909","title":"BERT for Joint Intent Classification and Slot Filling","created":"2019-02-28","cited_by_count":196},{"id":"2301.13670","title":"What Makes Good Examples for Visual In-Context Learning?","created":"2023-01-31","cited_by_count":150},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147},{"id":"2004.03829","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","created":"2020-04-08","cited_by_count":139},{"id":"1803.05567","title":"Achieving Human Parity on Automatic Chinese to English News Translation","created":"2018-03-15","cited_by_count":119},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117},{"id":"1712.01996","title":"An analysis of incorporating an external language model into a sequence-to-sequence model","created":"2017-12-06","cited_by_count":111},{"id":"1612.02695","title":"Towards better decoding and language model integration in sequence to sequence models","created":"2016-12-08","cited_by_count":100},{"id":"2106.09296","title":"Voice2Series: Reprogramming Acoustic Models for Time Series Classification","created":"2021-06-17","cited_by_count":91},{"id":"1708.06426","title":"Cold Fusion: Training Seq2Seq Models Together with Language Models","created":"2017-08-21","cited_by_count":88},{"id":"2010.11745","title":"Rethinking Evaluation in ASR: Are Our Models Robust Enough?","created":"2020-10-22","cited_by_count":73},{"id":"1807.10857","title":"A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition","created":"2018-07-27","cited_by_count":66},{"id":"2003.07962","title":"Deliberation Model Based Two-Pass End-to-End Speech Recognition","created":"2020-03-17","cited_by_count":57},{"id":"2003.07692","title":"ASR Error Correction and Domain Adaptation Using Machine Translation","created":"2020-03-13","cited_by_count":48},{"id":"2007.05916","title":"The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results","created":"2020-07-12","cited_by_count":44},{"id":"2105.03842","title":"FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition","created":"2021-05-09","cited_by_count":43},{"id":"2303.00456","title":"N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space","created":"2023-03-01","cited_by_count":42},{"id":"2212.10670","title":"In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models","created":"2022-12-20","cited_by_count":37},{"id":"1805.03294","title":"Improved training of end-to-end attention models for speech recognition","created":"2018-05-08","cited_by_count":36},{"id":"2303.00733","title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","created":"2023-03-01","cited_by_count":32},{"id":"2203.15321","title":"Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data","created":"2022-03-29","cited_by_count":30},{"id":"2101.11577","title":"Transformer Based Deliberation for Two-Pass Speech Recognition","created":"2021-01-27","cited_by_count":29},{"id":"2109.14420","title":"FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition","created":"2021-09-29","cited_by_count":27},{"id":"2204.00212","title":"Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems","created":"2022-04-01","cited_by_count":23},{"id":"2301.07851","title":"From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition","created":"2023-01-19","cited_by_count":23},{"id":"2306.02207","title":"SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts","created":"2023-06-03","cited_by_count":21},{"id":"2104.05507","title":"BART based semantic correction for Mandarin automatic speech recognition system","created":"2021-03-26","cited_by_count":20},{"id":"2010.03432","title":"WER we are and WER we think we are","created":"2020-10-07","cited_by_count":19},{"id":"2202.01157","title":"Error Correction in ASR using Sequence-to-Sequence Models","created":"2022-02-02","cited_by_count":19},{"id":"2212.10873","title":"Prompt-Augmented Linear Probing: Scaling beyond the Limit of Few-shot In-Context Learners","created":"2022-12-21","cited_by_count":18},{"id":"2305.04572","title":"Putting Natural in Natural Language Processing","created":"2023-05-08","cited_by_count":17},{"id":"1912.03363","title":"Audio-attention discriminative language model for ASR rescoring","created":"2019-12-06","cited_by_count":13},{"id":"2112.11442","title":"Deliberation of Streaming RNN-Transducer by Non-autoregressive Decoding","created":"2021-12-01","cited_by_count":13},{"id":"2001.05284","title":"Improving Spoken Language Understanding By Exploiting ASR N-best Hypotheses","created":"2020-01-11","cited_by_count":12},{"id":"1910.11450","title":"An Empirical Study of Efficient ASR Rescoring with Transformers","created":"2019-10-24","cited_by_count":11},{"id":"2211.13252","title":"Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction","created":"2022-11-23","cited_by_count":10},{"id":"2306.01015","title":"How to Estimate Model Transferability of Pre-Trained Speech Models?","created":"2023-06-01","cited_by_count":10},{"id":"2212.01039","title":"SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition","created":"2022-12-02","cited_by_count":9},{"id":"1904.03576","title":"Spoken Language Intent Detection using Confusion2Vec","created":"2019-04-07","cited_by_count":8},{"id":"2210.05785","title":"Scaling Up Deliberation for Multilingual ASR","created":"2022-10-11","cited_by_count":6},{"id":"1904.10045","title":"Automatic Spelling Correction with Transformer for CTC-based End-to-End Speech Recognition","created":"2019-03-27","cited_by_count":4},{"id":"1606.00210","title":"Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction","created":"2016-06-01","cited_by_count":3}],"next_cursor":null}