{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"1904.03670","title":"Speech Model Pre-training for End-to-End Spoken Language Understanding","created":"2019-04-07","cited_by_count":193},{"id":"2007.06028","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","created":"2020-07-12","cited_by_count":188},{"id":"2108.02035","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","created":"2021-08-04","cited_by_count":183},{"id":"2202.01855","title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition","created":"2022-02-03","cited_by_count":162},{"id":"2107.05604","title":"Direct speech-to-speech translation with discrete units","created":"2021-07-12","cited_by_count":149},{"id":"2109.03264","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","created":"2021-09-07","cited_by_count":119},{"id":"1904.06037","title":"Direct speech-to-speech translation with a sequence-to-sequence model","created":"2019-04-12","cited_by_count":118},{"id":"1806.11146","title":"Adversarial Reprogramming of Neural Networks","created":"2018-06-28","cited_by_count":116},{"id":"2002.02848","title":"Unsupervised pretraining transfers well across languages","created":"2020-02-07","cited_by_count":101},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100},{"id":"2010.13641","title":"Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification","created":"2020-10-26","cited_by_count":98},{"id":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94},{"id":"1910.12607","title":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","created":"2019-10-23","cited_by_count":82},{"id":"2012.06659","title":"DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization","created":"2020-12-11","cited_by_count":77},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77},{"id":"2202.10629","title":"Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning","created":"2022-02-22","cited_by_count":64},{"id":"2304.01448","title":"TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio","created":"2023-04-04","cited_by_count":59},{"id":"2203.09770","title":"Prototypical Verbalizer for Prompt-based Few-shot Tuning","created":"2022-03-18","cited_by_count":53},{"id":"2104.11462","title":"LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech","created":"2021-04-23","cited_by_count":47},{"id":"2204.02967","title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation","created":"2022-04-06","cited_by_count":44},{"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":"2309.15800","title":"Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study","created":"2023-09-27","cited_by_count":42},{"id":"2010.13826","title":"Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining","created":"2020-10-26","cited_by_count":35},{"id":"2010.13991","title":"Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning","created":"2020-10-27","cited_by_count":34},{"id":"2210.15759","title":"Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge","created":"2022-10-27","cited_by_count":34},{"id":"2206.02119","title":"A Multimodal Corpus for Emotion Recognition in Sarcasm","created":"2022-06-05","cited_by_count":29},{"id":"2202.07359","title":"textless-lib: a Library for Textless Spoken Language Processing","created":"2022-02-15","cited_by_count":28},{"id":"2305.18108","title":"Exploration of Efficient End-to-End ASR using Discretized Input from Self-Supervised Learning","created":"2023-05-29","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":"2205.01086","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","created":"2022-05-02","cited_by_count":26},{"id":"2203.05936","title":"Are discrete units necessary for Spoken Language Modeling?","created":"2022-03-11","cited_by_count":24},{"id":"2309.07377","title":"Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS","created":"2023-09-14","cited_by_count":24},{"id":"2005.07973","title":"AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition","created":"2020-05-16","cited_by_count":19},{"id":"2008.01994","title":"Improving End-to-End Speech-to-Intent Classification with Reptile","created":"2020-08-05","cited_by_count":17},{"id":"2010.13886","title":"MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection","created":"2020-10-26","cited_by_count":12},{"id":"2110.03894","title":"Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition","created":"2021-10-08","cited_by_count":3},{"id":"2310.02971","title":"Prompting and Adapter Tuning for Self-supervised Encoder-Decoder Speech Model","created":"2023-10-04","cited_by_count":3}],"next_cursor":null}