{"total":91,"rows":[{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148,"area":null},{"id":"2210.00077","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","created":"2022-09-30","cited_by_count":92,"area":null},{"id":"2206.05807","title":"Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation","created":"2022-06-12","cited_by_count":57,"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":"2110.01500","title":"Factorized Neural Transducer for Efficient Language Model Adaptation","created":"2021-09-27","cited_by_count":32,"area":null},{"id":"2110.09714","title":"Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information","created":"2021-10-19","cited_by_count":25,"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":"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":"2308.03266","title":"SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability","created":"2023-08-07","cited_by_count":18,"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":"2507.05727","title":"ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark","created":"2025-07-08","cited_by_count":15,"area":null},{"id":"2305.12498","title":"Multi-Head State Space Model for Speech Recognition","created":"2023-05-21","cited_by_count":14,"area":null},{"id":"2305.12839","title":"CopyNE: Better Contextual ASR by Copying Named Entities","created":"2023-05-22","cited_by_count":14,"area":null},{"id":"2406.16107","title":"Decoder-only Architecture for Streaming End-to-end Speech Recognition","created":"2024-06-23","cited_by_count":13,"area":null},{"id":"2102.09114","title":"Echo State Speech Recognition","created":"2021-02-18","cited_by_count":11,"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":"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":"2303.10949","title":"Code-Switching Text Generation and Injection in Mandarin-English ASR","created":"2023-03-20","cited_by_count":11,"area":null},{"id":"2104.02219","title":"Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction","created":"2021-04-06","cited_by_count":10,"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":"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":"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":"2401.04152","title":"Cross-Speaker Encoding Network for Multi-Talker Speech Recognition","created":"2024-01-08","cited_by_count":9,"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":"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":"2104.03842","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":"2108.13630","title":"SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory","created":"2021-08-31","cited_by_count":7,"area":null},{"id":"2211.01522","title":"Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2212.10818","title":"4D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoders","created":"2022-12-21","cited_by_count":7,"area":null},{"id":"2201.01209","title":"Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Question","created":"2022-01-04","cited_by_count":6,"area":null},{"id":"2201.12155","title":"Reducing language context confusion for end-to-end code-switching automatic speech recognition","created":"2022-01-28","cited_by_count":6,"area":null},{"id":"2203.00725","title":"A Conformer Based Acoustic Model for Robust Automatic Speech Recognition","created":"2022-03-01","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},{"id":"2207.11697","title":"Improving Mandarin Speech Recogntion with Block-augmented Transformer","created":"2022-07-24","cited_by_count":6,"area":null},{"id":"2306.08582","title":"Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data","created":"2023-06-14","cited_by_count":6,"area":null},{"id":"2102.07259","title":"Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2203.02317","title":"Adaptive Discounting of Implicit Language Models in RNN-Transducers","created":"2022-02-21","cited_by_count":5,"area":null},{"id":"2107.01569","title":"Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition","created":"2021-07-04","cited_by_count":4,"area":null},{"id":"2107.03007","title":"Advancing CTC-CRF Based End-to-End Speech Recognition with Wordpieces and Conformers","created":"2021-07-07","cited_by_count":4,"area":null},{"id":"2205.12462","title":"Improving CTC-based ASR Models with Gated Interlayer Collaboration","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2210.09188","title":"Sub-8-bit quantization for on-device speech recognition: a regularization-free approach","created":"2022-10-17","cited_by_count":4,"area":null},{"id":"2307.05006","title":"Improving RNN-Transducers with Acoustic LookAhead","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2307.08217","title":"BASS: Block-wise Adaptation for Speech Summarization","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2406.02950","title":"Joint Beam Search Integrating CTC, Attention, and Transducer Decoders","created":"2024-06-05","cited_by_count":4,"area":null},{"id":"2409.12388","title":"Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2107.05382","title":"End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning","created":"2021-07-07","cited_by_count":3,"area":null},{"id":"2203.16868","title":"Memory-Efficient Training of RNN-Transducer with Sampled Softmax","created":"2022-03-31","cited_by_count":3,"area":null},{"id":"2208.01818","title":"VQ-T: RNN Transducers using Vector-Quantized Prediction Network States","created":"2022-08-03","cited_by_count":3,"area":null},{"id":"2212.04325","title":"Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2302.11186","title":"UML: A Universal Monolingual Output Layer for Multilingual ASR","created":"2023-02-22","cited_by_count":3,"area":null},{"id":"2106.04275","title":"Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition","created":"2021-06-08","cited_by_count":2,"area":null},{"id":"2108.10752","title":"Generalizing RNN-Transducer to Out-Domain Audio via Sparse Self-Attention Layers","created":"2021-08-22","cited_by_count":2,"area":null},{"id":"2110.03326","title":"Back from the future: bidirectional CTC decoding using future information in speech recognition","created":"2021-10-07","cited_by_count":2,"area":null},{"id":"2206.12829","title":"On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode","created":"2022-06-26","cited_by_count":2,"area":null},{"id":"2207.02393","title":"Compute Cost Amortized Transformer for Streaming ASR","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2305.12518","title":"VAKTA-SETU: A Speech-to-Speech Machine Translation Service in Select Indic Languages","created":"2023-05-21","cited_by_count":2,"area":null},{"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":"2102.08154","title":"End-to-End Automatic Speech Recognition with Deep Mutual Learning","created":"2021-02-16","cited_by_count":1,"area":null},{"id":"2103.01661","title":"Incorporating VAD into ASR System by Multi-task Learning","created":"2021-03-02","cited_by_count":1,"area":null},{"id":"2104.10764","title":"HMM-Free Encoder Pre-Training for Streaming RNN Transducer","created":"2021-04-02","cited_by_count":1,"area":null},{"id":"2105.05920","title":"Attention-based Neural Beamforming Layers for Multi-channel Speech Recognition","created":"2021-05-12","cited_by_count":1,"area":null},{"id":"2201.06026","title":"Toward Among-Device AI from On-Device AI with Stream Pipelines","created":"2022-01-16","cited_by_count":1,"area":null},{"id":"2205.14664","title":"Heterogeneous Data-Centric Architectures for Modern Data-Intensive Applications: Case Studies in Machine Learning and Databases","created":"2022-05-29","cited_by_count":1,"area":null},{"id":"2208.02250","title":"Adversarial Attacks on ASR Systems: An Overview","created":"2022-08-03","cited_by_count":1,"area":null},{"id":"2210.16892","title":"Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2211.16270","title":"Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2302.09723","title":"Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition","created":"2023-02-20","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":"2310.05886","title":"Streaming Anchor Loss: Augmenting Supervision with Temporal Significance","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2311.14835","title":"Weak Alignment Supervision from Hybrid Model Improves End-to-end ASR","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2311.16595","title":"D4AM: A General Denoising Framework for Downstream Acoustic Models","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2401.05700","title":"R-BI: Regularized Batched Inputs enhance Incremental Decoding Framework for Low-Latency Simultaneous Speech Translation","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2502.05232","title":"Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2506.14434","title":"Unifying Streaming and Non-streaming Zipformer-based ASR","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2509.04393","title":"Contextualized Token Discrimination for Speech Search Query Correction","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2201.12105","title":"Improving End-to-End Models for Set Prediction in Spoken Language Understanding","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2203.15613","title":"Dynamic Latency for CTC-Based Streaming Automatic Speech Recognition With Emformer","created":"2022-03-29","cited_by_count":0,"area":null},{"id":"2308.02870","title":"ApproBiVT: Lead ASR Models to Generalize Better Using Approximated Bias-Variance Tradeoff Guided Early Stopping and Checkpoint Averaging","created":"2023-08-05","cited_by_count":0,"area":null},{"id":"2310.07345","title":"Investigating the Effect of Language Models in Sequence Discriminative Training for Neural Transducers","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2402.15594","title":"Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASR","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2407.17605","title":"Coupling Speech Encoders with Downstream Text Models","created":"2024-07-24","cited_by_count":0,"area":null},{"id":"2411.14489","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2603.01382","title":"End-to-End Simultaneous Dysarthric Speech Reconstruction with Frame-Level Adaptor and Multiple Wait-k Knowledge Distillation","created":"2026-03-02","cited_by_count":0,"area":null}],"next_cursor":null}