{"list":"other","total":59,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"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":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"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":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"1909.05855","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","created":"2019-09-12","cited_by_count":434},{"id":"2003.04807","title":"Efficient Intent Detection with Dual Sentence Encoders","created":"2020-03-10","cited_by_count":433},{"id":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"id":"1808.09602","title":"Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction","created":"2018-08-29","cited_by_count":322},{"id":"2002.02562","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","created":"2020-02-07","cited_by_count":235},{"id":"2007.12720","title":"MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines","created":"2020-07-10","cited_by_count":204},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"2302.03540","title":"Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision","created":"2023-02-07","cited_by_count":169},{"id":"2005.09629","title":"Improved Noisy Student Training for Automatic Speech Recognition","created":"2020-05-19","cited_by_count":141},{"id":"2012.04373","title":"CrossNER: Evaluating Cross-Domain Named Entity Recognition","created":"2020-12-08","cited_by_count":104},{"id":"2005.03191","title":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","created":"2020-05-07","cited_by_count":97},{"id":"2002.12328","title":"Few-shot Natural Language Generation for Task-Oriented Dialog","created":"2020-02-27","cited_by_count":89},{"id":"2111.02735","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","created":"2021-11-04","cited_by_count":82},{"id":"2204.03409","title":"MAESTRO: Matched Speech Text Representations through Modality Matching","created":"2022-04-07","cited_by_count":79},{"id":"1910.12977","title":"Transformer-Transducer: End-to-End Speech Recognition with Self-Attention","created":"2019-10-28","cited_by_count":69},{"id":"2110.10329","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","created":"2021-10-20","cited_by_count":69},{"id":"2106.09660","title":"WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis","created":"2021-06-17","cited_by_count":65},{"id":"1905.03072","title":"RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation","created":"2019-05-08","cited_by_count":63},{"id":"1912.05533","title":"SpecAugment on Large Scale Datasets","created":"2019-12-11","cited_by_count":60},{"id":"2111.14706","title":"ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet","created":"2021-11-29","cited_by_count":53},{"id":"2209.15329","title":"SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data","created":"2022-09-30","cited_by_count":49},{"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},{"id":"2010.04284","title":"Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systems","created":"2020-10-08","cited_by_count":38},{"id":"1805.07467","title":"Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces","created":"2018-05-18","cited_by_count":34},{"id":"2002.03788","title":"Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior","created":"2020-02-06","cited_by_count":33},{"id":"2002.01359","title":"Schema-Guided Dialogue State Tracking Task at DSTC8","created":"2020-02-02","cited_by_count":32},{"id":"2005.07157","title":"You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation","created":"2020-05-14","cited_by_count":29},{"id":"2102.06283","title":"Speech-language Pre-training for End-to-end Spoken Language Understanding","created":"2021-02-11","cited_by_count":27},{"id":"1909.13037","title":"Self-Attention Transducers for End-to-End Speech Recognition","created":"2019-09-28","cited_by_count":24},{"id":"1910.09463","title":"Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models","created":"2019-10-21","cited_by_count":24},{"id":"2008.05750","title":"Conv-Transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-End Speech Recognition","created":"2020-08-13","cited_by_count":23},{"id":"2106.14464","title":"Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU","created":"2021-06-28","cited_by_count":22},{"id":"2207.10643","title":"STOP: A dataset for Spoken Task Oriented Semantic Parsing","created":"2022-06-29","cited_by_count":22},{"id":"2009.13833","title":"HINT3: Raising the bar for Intent Detection in the Wild","created":"2020-09-29","cited_by_count":21},{"id":"2202.13155","title":"Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models","created":"2022-02-26","cited_by_count":20},{"id":"2010.12283","title":"ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding","created":"2020-10-23","cited_by_count":19},{"id":"2201.10207","title":"SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training","created":"2022-01-25","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":"2102.07370","title":"Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classification","created":"2021-02-15","cited_by_count":11},{"id":"2104.03842","title":"RNN Transducer Models For Spoken Language Understanding","created":"2021-04-08","cited_by_count":7},{"id":"2204.05483","title":"Redwood: Using Collision Detection to Grow a Large-Scale Intent Classification Dataset","created":"2022-04-12","cited_by_count":6}],"next_cursor":null}