{"total":212,"rows":[{"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":"2104.02194","title":"Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion","created":"2021-04-05","cited_by_count":101,"area":null},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88,"area":null},{"id":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79,"area":null},{"id":"2101.07597","title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","created":"2021-01-19","cited_by_count":77,"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":"2205.13660","title":"Contextual Adapters for Personalized Speech Recognition in Neural Transducers","created":"2022-05-26","cited_by_count":57,"area":null},{"id":"2111.03250","title":"Context-Aware Transformer Transducer for Speech Recognition","created":"2021-11-05","cited_by_count":56,"area":null},{"id":"2203.15455","title":"WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit","created":"2022-03-29","cited_by_count":47,"area":null},{"id":"2206.13236","title":"Pruned RNN-T for fast, memory-efficient ASR training","created":"2022-06-23","cited_by_count":46,"area":null},{"id":"2103.09935","title":"Advancing RNN Transducer Technology for Speech Recognition","created":"2021-03-17","cited_by_count":44,"area":null},{"id":"2109.01163","title":"Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition","created":"2021-08-31","cited_by_count":42,"area":null},{"id":"2201.12806","title":"Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection","created":"2022-01-30","cited_by_count":39,"area":null},{"id":"2109.07513","title":"Tied & Reduced RNN-T Decoder","created":"2021-09-15","cited_by_count":36,"area":null},{"id":"2106.07803","title":"SynthASR: Unlocking Synthetic Data for Speech Recognition","created":"2021-06-14","cited_by_count":34,"area":null},{"id":"2202.01094","title":"RescoreBERT: Discriminative Speech Recognition Rescoring with BERT","created":"2022-02-02","cited_by_count":34,"area":null},{"id":"2109.00627","title":"Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition","created":"2021-09-01","cited_by_count":32,"area":null},{"id":"2109.11641","title":"Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detection","created":"2021-09-23","cited_by_count":32,"area":null},{"id":"2110.01500","title":"Factorized Neural Transducer for Efficient Language Model Adaptation","created":"2021-09-27","cited_by_count":32,"area":null},{"id":"2110.04621","title":"Universal Paralinguistic Speech Representations Using Self-Supervised Conformers","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2109.06952","title":"Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech","created":"2021-09-14","cited_by_count":31,"area":null},{"id":"2305.12493","title":"Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network","created":"2023-05-21","cited_by_count":31,"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":"2110.11346","title":"Data-Driven Offline Optimization For Architecting Hardware Accelerators","created":"2021-10-20","cited_by_count":29,"area":null},{"id":"2102.07739","title":"Personalization Strategies for End-to-End Speech Recognition Systems","created":"2021-02-15","cited_by_count":26,"area":null},{"id":"2104.09426","title":"Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers","created":"2021-04-19","cited_by_count":25,"area":null},{"id":"2312.17279","title":"Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition","created":"2023-12-27","cited_by_count":25,"area":null},{"id":"2111.00161","title":"Pseudo-Labeling for Massively Multilingual Speech Recognition","created":"2021-10-30","cited_by_count":24,"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":"2209.06058","title":"Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification","created":"2022-09-13","cited_by_count":24,"area":null},{"id":"2210.07353","title":"JOIST: A Joint Speech and Text Streaming Model For ASR","created":"2022-10-13","cited_by_count":24,"area":null},{"id":"2109.14320","title":"Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks","created":"2021-09-29","cited_by_count":23,"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":"2103.06716","title":"Learning Word-Level Confidence For Subword End-to-End ASR","created":"2021-03-11","cited_by_count":22,"area":null},{"id":"2202.13155","title":"Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models","created":"2022-02-26","cited_by_count":20,"area":null},{"id":"2203.00006","title":"Towards Reducing the Need for Speech Training Data To Build Spoken Language Understanding Systems","created":"2022-02-26","cited_by_count":20,"area":null},{"id":"2104.02207","title":"Dissecting User-Perceived Latency of On-Device E2E Speech Recognition","created":"2021-04-06","cited_by_count":19,"area":null},{"id":"2104.11127","title":"Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network","created":"2021-04-22","cited_by_count":19,"area":null},{"id":"2105.00858","title":"On Addressing Practical Challenges for RNN-Transducer","created":"2021-04-27","cited_by_count":19,"area":null},{"id":"2106.02302","title":"Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition","created":"2021-06-04","cited_by_count":19,"area":null},{"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,"area":null},{"id":"2305.05271","title":"Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition","created":"2023-05-09","cited_by_count":18,"area":null},{"id":"2203.00888","title":"Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems","created":"2022-03-02","cited_by_count":17,"area":null},{"id":"2210.16481","title":"Accelerating RNN-T Training and Inference Using CTC guidance","created":"2022-10-29","cited_by_count":17,"area":null},{"id":"2211.09019","title":"Learning Reward Functions for Robotic Manipulation by Observing Humans","created":"2022-11-16","cited_by_count":17,"area":null},{"id":"2211.05756","title":"Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities","created":"2022-11-10","cited_by_count":16,"area":null},{"id":"2208.13321","title":"Turn-Taking Prediction for Natural Conversational Speech","created":"2022-08-29","cited_by_count":15,"area":null},{"id":"2110.04612","title":"Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasets","created":"2021-10-09","cited_by_count":14,"area":null},{"id":"2401.05336","title":"Towards Online Continuous Sign Language Recognition and Translation","created":"2024-01-10","cited_by_count":14,"area":null},{"id":"2104.02109","title":"Streaming Multi-talker Speech Recognition with Joint Speaker Identification","created":"2021-04-05","cited_by_count":13,"area":null},{"id":"2112.11442","title":"Deliberation of Streaming RNN-Transducer by Non-autoregressive Decoding","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2203.16536","title":"Recent improvements of ASR models in the face of adversarial attacks","created":"2022-03-29","cited_by_count":13,"area":null},{"id":"2106.07167","title":"End-to-end Neural Diarization: From Transformer to Conformer","created":"2021-06-14","cited_by_count":12,"area":null},{"id":"2110.08352","title":"Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2204.03793","title":"Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition","created":"2022-04-08","cited_by_count":12,"area":null},{"id":"2209.05735","title":"Learning ASR pathways: A sparse multilingual ASR model","created":"2022-09-13","cited_by_count":12,"area":null},{"id":"2211.02499","title":"A Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capability","created":"2022-11-04","cited_by_count":12,"area":null},{"id":"2301.06735","title":"Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducer","created":"2023-01-17","cited_by_count":12,"area":null},{"id":"2306.00804","title":"Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognition","created":"2023-06-01","cited_by_count":12,"area":null},{"id":"2104.02882","title":"FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization","created":"2021-04-07","cited_by_count":11,"area":null},{"id":"2108.07493","title":"A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems","created":"2021-08-17","cited_by_count":11,"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":"2204.06164","title":"A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes","created":"2022-04-13","cited_by_count":11,"area":null},{"id":"2205.09058","title":"Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator","created":"2022-05-18","cited_by_count":11,"area":null},{"id":"2212.01992","title":"Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition models","created":"2022-12-05","cited_by_count":11,"area":null},{"id":"2304.09607","title":"CB-Conformer: Contextual biasing Conformer for biased word recognition","created":"2023-04-19","cited_by_count":11,"area":null},{"id":"2104.03587","title":"WNARS: WFST based Non-autoregressive Streaming End-to-End Speech Recognition","created":"2021-04-08","cited_by_count":10,"area":null},{"id":"2106.01604","title":"Noisy student-teacher training for robust keyword spotting","created":"2021-06-03","cited_by_count":10,"area":null},{"id":"2108.00084","title":"The History of Speech Recognition to the Year 2030","created":"2021-07-30","cited_by_count":10,"area":null},{"id":"2211.02809","title":"LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2302.08917","title":"Massively Multilingual Shallow Fusion with Large Language Models","created":"2023-02-17","cited_by_count":10,"area":null},{"id":"2104.02176","title":"Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency","created":"2021-04-05","cited_by_count":9,"area":null},{"id":"2108.08405","title":"Integrating Dialog History into End-to-End Spoken Language Understanding Systems","created":"2021-08-18","cited_by_count":9,"area":null},{"id":"2111.10770","title":"Efficient Softmax Approximation for Deep Neural Networks with Attention Mechanism","created":"2021-11-21","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":"2302.11192","title":"Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation","created":"2023-02-22","cited_by_count":9,"area":null},{"id":"2102.11531","title":"Memory-efficient Speech Recognition on Smart Devices","created":"2021-02-23","cited_by_count":8,"area":null},{"id":"2104.04487","title":"Language model fusion for streaming end to end speech recognition","created":"2021-04-09","cited_by_count":8,"area":null},{"id":"2104.13970","title":"Personalized Keyphrase Detection using Speaker and Environment Information","created":"2021-04-28","cited_by_count":8,"area":null},{"id":"2105.07071","title":"Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End","created":"2021-05-14","cited_by_count":8,"area":null},{"id":"2108.12074","title":"4-bit Quantization of LSTM-based Speech Recognition Models","created":"2021-08-27","cited_by_count":8,"area":null},{"id":"2108.12953","title":"Multi-Channel Transformer Transducer for Speech Recognition","created":"2021-08-30","cited_by_count":8,"area":null},{"id":"2203.15773","title":"Streaming parallel transducer beam search with fast-slow cascaded encoders","created":"2022-03-29","cited_by_count":8,"area":null},{"id":"2207.03169","title":"End-to-end Speech-to-Punctuated-Text Recognition","created":"2022-07-07","cited_by_count":8,"area":null},{"id":"2209.14868","title":"ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition","created":"2022-09-29","cited_by_count":8,"area":null},{"id":"2101.05453","title":"On the quantization of recurrent neural networks","created":"2021-01-14","cited_by_count":7,"area":null},{"id":"2103.00768","title":"Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2104.00766","title":"Configurable Privacy-Preserving Automatic Speech Recognition","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2104.01522","title":"TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition","created":"2021-04-04","cited_by_count":7,"area":null},{"id":"2104.03842","title":"RNN Transducer Models For Spoken Language Understanding","created":"2021-04-08","cited_by_count":7,"area":null},{"id":"2106.04660","title":"Sequential End-to-End Intent and Slot Label Classification and Localization","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2106.08960","title":"Collaborative Training of Acoustic Encoders for Speech Recognition","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2110.04891","title":"Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition","created":"2021-10-10","cited_by_count":7,"area":null},{"id":"2110.07982","title":"Scribosermo: Fast Speech-to-Text models for German and other Languages","created":"2021-10-15","cited_by_count":7,"area":null},{"id":"2206.13240","title":"A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data","created":"2022-06-22","cited_by_count":7,"area":null},{"id":"2301.00304","title":"Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greek","created":"2022-12-31","cited_by_count":7,"area":null},{"id":"2110.14812","title":"Differentiable NAS Framework and Application to Ads CTR Prediction","created":"2021-10-25","cited_by_count":6,"area":null},{"id":"2201.11867","title":"Neural-FST Class Language Model for End-to-End Speech Recognition","created":"2022-01-28","cited_by_count":6,"area":null},{"id":"2203.15966","title":"Federated Domain Adaptation for ASR with Full Self-Supervision","created":"2022-03-30","cited_by_count":6,"area":null}],"next_cursor":"100"}