{"total":86,"rows":[{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631,"area":"moe"},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295,"area":null},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274,"area":null},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897,"area":"wm"},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647,"area":"mllm"},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224,"area":null},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187,"area":null},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164,"area":null},{"id":"2202.01855","title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition","created":"2022-02-03","cited_by_count":162,"area":null},{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140,"area":null},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2111.09388","title":"High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics","created":"2021-11-17","cited_by_count":104,"area":null},{"id":"2107.08661","title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","created":"2021-07-19","cited_by_count":71,"area":null},{"id":"2201.03713","title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","created":"2022-01-11","cited_by_count":71,"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":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2104.14830","title":"Scaling End-to-End Models for Large-Scale Multilingual ASR","created":"2021-04-30","cited_by_count":61,"area":null},{"id":"2205.04596","title":"When does dough become a bagel? Analyzing the remaining mistakes on ImageNet","created":"2022-05-09","cited_by_count":61,"area":null},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2103.01306","title":"Scalable Scene Flow from Point Clouds in the Real World","created":"2021-03-01","cited_by_count":50,"area":null},{"id":"2103.03344","title":"WaveGuard: Understanding and Mitigating Audio Adversarial Examples","created":"2021-03-04","cited_by_count":40,"area":null},{"id":"2109.07513","title":"Tied & Reduced RNN-T Decoder","created":"2021-09-15","cited_by_count":36,"area":null},{"id":"2309.10966","title":"MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods","created":"2023-09-19","cited_by_count":33,"area":null},{"id":"2101.11577","title":"Transformer Based Deliberation for Two-Pass Speech Recognition","created":"2021-01-27","cited_by_count":29,"area":null},{"id":"2203.15952","title":"4-bit Conformer with Native Quantization Aware Training for Speech Recognition","created":"2022-03-29","cited_by_count":24,"area":null},{"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,"area":null},{"id":"2303.01507","title":"Defending against Adversarial Audio via Diffusion Model","created":"2023-03-02","cited_by_count":23,"area":"diffusion"},{"id":"2103.06716","title":"Learning Word-Level Confidence For Subword End-to-End ASR","created":"2021-03-11","cited_by_count":22,"area":null},{"id":"2108.13990","title":"Effective Sequence-to-Sequence Dialogue State Tracking","created":"2021-08-31","cited_by_count":20,"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":"2101.08809","title":"PyGlove: Symbolic Programming for Automated Machine Learning","created":"2021-01-21","cited_by_count":19,"area":null},{"id":"2201.03110","title":"Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learning","created":"2022-01-09","cited_by_count":19,"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":"2210.13352","title":"ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition","created":"2022-10-24","cited_by_count":18,"area":null},{"id":"2111.00556","title":"Revealing and Protecting Labels in Distributed Training","created":"2021-10-31","cited_by_count":17,"area":null},{"id":"2204.10749","title":"E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR","created":"2022-04-22","cited_by_count":17,"area":null},{"id":"2302.01496","title":"Efficient Domain Adaptation for Speech Foundation Models","created":"2023-02-03","cited_by_count":13,"area":null},{"id":"2106.04060","title":"Self-supervised and Supervised Joint Training for Resource-rich Machine Translation","created":"2021-06-08","cited_by_count":12,"area":null},{"id":"2201.10240","title":"Improving the fusion of acoustic and text representations in RNN-T","created":"2022-01-25","cited_by_count":11,"area":null},{"id":"2104.02757","title":"Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models","created":"2021-04-06","cited_by_count":10,"area":null},{"id":"2110.03841","title":"Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition","created":"2021-10-08","cited_by_count":10,"area":null},{"id":"2212.10422","title":"Localising In-Domain Adaptation of Transformer-Based Biomedical Language Models","created":"2022-12-20","cited_by_count":10,"area":null},{"id":"2304.04596","title":"ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit","created":"2023-04-10","cited_by_count":10,"area":null},{"id":"2104.04552","title":"Lookup-Table Recurrent Language Models for Long Tail Speech Recognition","created":"2021-04-09","cited_by_count":9,"area":null},{"id":"2201.11627","title":"Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASR","created":"2022-01-26","cited_by_count":9,"area":null},{"id":"2208.13916","title":"A Language Agnostic Multilingual Streaming On-Device ASR System","created":"2022-08-29","cited_by_count":9,"area":null},{"id":"2104.05146","title":"Assessing Reference-Free Peer Evaluation for Machine Translation","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2104.12870","title":"Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction","created":"2021-04-26","cited_by_count":8,"area":null},{"id":"2203.07627","title":"Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation","created":"2022-03-15","cited_by_count":7,"area":null},{"id":"2205.03494","title":"Online Model Compression for Federated Learning with Large Models","created":"2022-05-06","cited_by_count":7,"area":null},{"id":"2305.13408","title":"Modular Domain Adaptation for Conformer-Based Streaming ASR","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2106.05111","title":"A Comparative Study on Neural Architectures and Training Methods for Japanese Speech Recognition","created":"2021-06-09","cited_by_count":6,"area":null},{"id":"2202.12163","title":"Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech","created":"2022-02-24","cited_by_count":6,"area":null},{"id":"2210.05785","title":"Scaling Up Deliberation for Multilingual ASR","created":"2022-10-11","cited_by_count":6,"area":null},{"id":"2402.17184","title":"Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models","created":"2024-02-27","cited_by_count":6,"area":null},{"id":"2211.00786","title":"Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems","created":"2022-11-01","cited_by_count":5,"area":null},{"id":"2404.10180","title":"Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2103.08086","title":"Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systems","created":"2021-03-15","cited_by_count":4,"area":null},{"id":"2103.10651","title":"SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systems","created":"2021-03-19","cited_by_count":4,"area":null},{"id":"2106.15818","title":"On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation","created":"2021-06-30","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":"2103.08095","title":"Towards Robust Speech-to-Text Adversarial Attack","created":"2021-03-15","cited_by_count":3,"area":null},{"id":"2109.04443","title":"HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints","created":"2021-09-09","cited_by_count":3,"area":null},{"id":"2201.13156","title":"Low-Rank Updates of Matrix Square Roots","created":"2022-01-31","cited_by_count":3,"area":null},{"id":"2202.10594","title":"Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey","created":"2022-02-22","cited_by_count":3,"area":null},{"id":"2209.06096","title":"Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition","created":"2022-09-13","cited_by_count":3,"area":null},{"id":"2211.16594","title":"Exploiting Category Names for Few-Shot Classification with Vision-Language Models","created":"2022-11-29","cited_by_count":3,"area":"mllm"},{"id":"2302.12961","title":"Locale Encoding For Scalable Multilingual Keyword Spotting Models","created":"2023-02-25","cited_by_count":3,"area":null},{"id":"2312.01532","title":"Using Large Language Models to Accelerate Communication for Users with Severe Motor Impairments","created":"2023-12-03","cited_by_count":3,"area":null},{"id":"2103.00109","title":"Improving Longer-range Dialogue State Tracking","created":"2021-02-27","cited_by_count":2,"area":null},{"id":"2203.05642","title":"Parameter-Free Attentive Scoring for Speaker Verification","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2205.00659","title":"The Implicit Length Bias of Label Smoothing on Beam Search Decoding","created":"2022-05-02","cited_by_count":2,"area":null},{"id":"2305.18419","title":"Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR","created":"2023-05-28","cited_by_count":2,"area":"distill"},{"id":"2312.11123","title":"Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2407.16840","title":"Synth4Kws: Synthesized Speech for User Defined Keyword Spotting in Low Resource Environments","created":"2024-07-23","cited_by_count":2,"area":null},{"id":"2410.16647","title":"GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-shot Keyword Spotting","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2202.00399","title":"Language Dependencies in Adversarial Attacks on Speech Recognition Systems","created":"2022-02-01","cited_by_count":1,"area":null},{"id":"2303.15293","title":"A Deliberation-based Joint Acoustic and Text Decoder","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2306.07949","title":"Improving Frame-level Classifier for Word Timings with Non-peaky CTC in End-to-End Automatic Speech Recognition","created":"2023-06-09","cited_by_count":1,"area":null},{"id":"2406.02133","title":"SimulTron: On-Device Simultaneous Speech to Speech Translation","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2207.06858","title":"RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attacks","created":"2022-07-14","cited_by_count":0,"area":null},{"id":"2302.01918","title":"PyGlove: Efficiently Exchanging ML Ideas as Code","created":"2023-02-03","cited_by_count":0,"area":null},{"id":"2306.01789","title":"Edit Distance based RL for RNNT decoding","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2507.23292","title":"SequenceLayers: Sequence Processing and Streaming Neural Networks Made Easy","created":"2025-07-31","cited_by_count":0,"area":null}],"next_cursor":null}