{"total":94,"rows":[{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2111.09344","title":"The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage","created":"2021-11-17","cited_by_count":101,"area":null},{"id":"2102.03216","title":"Intermediate Loss Regularization for CTC-based Speech Recognition","created":"2021-02-05","cited_by_count":96,"area":null},{"id":"2402.08846","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","created":"2024-02-13","cited_by_count":88,"area":null},{"id":"2310.11230","title":"Zipformer: A faster and better encoder for automatic speech recognition","created":"2023-10-17","cited_by_count":80,"area":null},{"id":"2104.02724","title":"Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions","created":"2021-04-06","cited_by_count":61,"area":null},{"id":"2206.00888","title":"Squeezeformer: An Efficient Transformer for Automatic Speech Recognition","created":"2022-06-02","cited_by_count":51,"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":"2106.08922","title":"Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition","created":"2021-06-16","cited_by_count":40,"area":null},{"id":"2204.00333","title":"PriMock57: A Dataset Of Primary Care Mock Consultations","created":"2022-04-01","cited_by_count":31,"area":null},{"id":"2110.05249","title":"A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation","created":"2021-10-11","cited_by_count":28,"area":null},{"id":"2307.13008","title":"Adaptation of Whisper models to child speech recognition","created":"2023-07-24","cited_by_count":26,"area":null},{"id":"2207.00555","title":"FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning","created":"2022-07-01","cited_by_count":25,"area":"distill"},{"id":"2301.01456","title":"Audio-Visual Efficient Conformer for Robust Speech Recognition","created":"2023-01-04","cited_by_count":22,"area":null},{"id":"2306.13734","title":"The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios","created":"2023-06-23","cited_by_count":22,"area":null},{"id":"2103.16827","title":"Integer-only Zero-shot Quantization for Efficient Speech Recognition","created":"2021-03-31","cited_by_count":19,"area":null},{"id":"2104.03416","title":"Pushing the Limits of Non-Autoregressive Speech Recognition","created":"2021-04-07","cited_by_count":18,"area":null},{"id":"2302.08137","title":"ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations","created":"2023-02-16","cited_by_count":15,"area":null},{"id":"2106.09216","title":"Layer Pruning on Demand with Intermediate CTC","created":"2021-06-17","cited_by_count":13,"area":null},{"id":"2406.03460","title":"The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement","created":"2024-06-05","cited_by_count":12,"area":null},{"id":"2204.00618","title":"ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion","created":"2022-03-29","cited_by_count":10,"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":"2104.08189","title":"TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction","created":"2021-04-16","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":"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":"2104.09995","title":"Review of end-to-end speech synthesis technology based on deep learning","created":"2021-04-20","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":"2301.07247","title":"Tailor: Altering Skip Connections for Resource-Efficient Inference","created":"2023-01-18","cited_by_count":6,"area":null},{"id":"2306.03014","title":"On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2409.18850","title":"Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2104.04896","title":"A Toolbox for Construction and Analysis of Speech Datasets","created":"2021-04-11","cited_by_count":5,"area":null},{"id":"2104.10121","title":"On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era","created":"2021-04-20","cited_by_count":5,"area":null},{"id":"2106.03895","title":"SIGTYP 2021 Shared Task: Robust Spoken Language Identification","created":"2021-06-07","cited_by_count":5,"area":null},{"id":"2203.10473","title":"ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis","created":"2022-03-20","cited_by_count":5,"area":null},{"id":"2207.01052","title":"Generating gender-ambiguous voices for privacy-preserving speech recognition","created":"2022-07-03","cited_by_count":5,"area":null},{"id":"2208.07657","title":"Uconv-Conformer: High Reduction of Input Sequence Length for End-to-End Speech Recognition","created":"2022-08-16","cited_by_count":5,"area":null},{"id":"2210.15781","title":"A Compact End-to-End Model with Local and Global Context for Spoken Language Identification","created":"2022-10-27","cited_by_count":5,"area":null},{"id":"2211.15075","title":"Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition","created":"2022-11-28","cited_by_count":5,"area":"distill"},{"id":"2310.09653","title":"SelfVC: Voice Conversion With Iterative Refinement using Self Transformations","created":"2023-10-14","cited_by_count":5,"area":null},{"id":"2405.15216","title":"Revisiting ASR Error Correction with Specialized Models","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2505.00059","title":"BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition","created":"2025-04-30","cited_by_count":5,"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":"2406.02950","title":"Joint Beam Search Integrating CTC, Attention, and Transducer Decoders","created":"2024-06-05","cited_by_count":4,"area":null},{"id":"2512.19442","title":"Real-Time Streamable Generative Speech Restoration with Flow Matching","created":"2025-12-22","cited_by_count":4,"area":"diffusion"},{"id":"2202.08456","title":"MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition","created":"2022-02-17","cited_by_count":3,"area":null},{"id":"2302.05040","title":"PATCorrect: Non-autoregressive Phoneme-augmented Transformer for ASR Error Correction","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2401.11144","title":"Towards Open-World Gesture Recognition","created":"2024-01-20","cited_by_count":3,"area":null},{"id":"2103.03142","title":"Error-driven Fixed-Budget ASR Personalization for Accented Speakers","created":"2021-03-04","cited_by_count":2,"area":null},{"id":"2103.07186","title":"Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition","created":"2021-03-12","cited_by_count":2,"area":null},{"id":"2103.17142","title":"Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matrices","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2202.00601","title":"BEA-Base: A Benchmark for ASR of Spontaneous Hungarian","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2206.14589","title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","created":"2022-06-29","cited_by_count":2,"area":null},{"id":"2210.05726","title":"Automatic Speech Recognition of Low-Resource Languages Based on Chukchi","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2306.09979","title":"Evaluation of Speech Representations for MOS prediction","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2311.04936","title":"A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognition","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2501.13230","title":"Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2511.18557","title":"Dealing with the Hard Facts of Low-Resource African NLP","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2103.03543","title":"Artificial Neural Networks generated by Low Discrepancy Sequences","created":"2021-03-05","cited_by_count":1,"area":null},{"id":"2104.08002","title":"Efficient and Generic 1D Dilated Convolution Layer for Deep Learning","created":"2021-04-16","cited_by_count":1,"area":null},{"id":"2104.11985","title":"Language ID Prediction from Speech Using Self-Attentive Pooling and 1D-Convolutions","created":"2021-04-24","cited_by_count":1,"area":null},{"id":"2204.05617","title":"ASR in German: A Detailed Error Analysis","created":"2022-04-12","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":"2303.15042","title":"Partially Adaptive Multichannel Joint Reduction of Ego-noise and Environmental Noise","created":"2023-03-27","cited_by_count":1,"area":null},{"id":"2305.16342","title":"InterFormer: Interactive Local and Global Features Fusion for Automatic Speech Recognition","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2309.09136","title":"Enhancing Quantised End-to-End ASR Models via Personalisation","created":"2023-09-17","cited_by_count":1,"area":null},{"id":"2406.06634","title":"Sparse Binarization for Fast Keyword Spotting","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2504.18950","title":"Speaker Retrieval in the Wild: Challenges, Effectiveness and Robustness","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2507.13977","title":"Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic","created":"2025-07-18","cited_by_count":1,"area":null},{"id":"2105.07520","title":"Dynamic Pooling Improves Nanopore Base Calling Accuracy","created":"2021-05-16","cited_by_count":0,"area":null},{"id":"2106.00052","title":"Low-Resource Spoken Language Identification Using Self-Attentive Pooling and Deep 1D Time-Channel Separable Convolutions","created":"2021-05-31","cited_by_count":0,"area":null},{"id":"2108.02034","title":"Dyn-ASR: Compact, Multilingual Speech Recognition via Spoken Language and Accent Identification","created":"2021-08-04","cited_by_count":0,"area":null},{"id":"2109.00916","title":"Coarse-To-Fine And Cross-Lingual ASR Transfer","created":"2021-09-02","cited_by_count":0,"area":null},{"id":"2111.03664","title":"Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models","created":"2021-11-05","cited_by_count":0,"area":"distill"},{"id":"2202.07750","title":"Nonverbal Sound Detection for Disordered Speech","created":"2022-02-15","cited_by_count":0,"area":null},{"id":"2205.05488","title":"DNA data storage, sequencing data-carrying DNA","created":"2022-05-11","cited_by_count":0,"area":null},{"id":"2207.01732","title":"DEFORMER: Coupling Deformed Localized Patterns with Global Context for Robust End-to-end Speech Recognition","created":"2022-07-04","cited_by_count":0,"area":null},{"id":"2209.00261","title":"Attention Enhanced Citrinet for Speech Recognition","created":"2022-09-01","cited_by_count":0,"area":null},{"id":"2210.00367","title":"A Comparison of Transformer, Convolutional, and Recurrent Neural Networks on Phoneme Recognition","created":"2022-10-01","cited_by_count":0,"area":null},{"id":"2211.00795","title":"InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss","created":"2022-11-02","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":"2309.17267","title":"Wiki-En-ASR-Adapt: Large-scale synthetic dataset for English ASR Customization","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2311.11030","title":"Data Center Audio/Video Intelligence on Device (DAVID) -- An Edge-AI Platform for Smart-Toys","created":"2023-11-18","cited_by_count":0,"area":null},{"id":"2408.00005","title":"Framework for Curating Speech Datasets and Evaluating ASR Systems: A Case Study for Polish","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2408.10243","title":"TrIM, Triangular Input Movement Systolic Array for Convolutional Neural Networks: Architecture and Hardware Implementation","created":"2024-08-05","cited_by_count":0,"area":null},{"id":"2409.00099","title":"Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2502.15228","title":"AutoMR: A Universal Time Series Motion Recognition Pipeline","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2505.06335","title":"Remote Rowhammer Attack using Adversarial Observations on Federated Learning Clients","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2511.15565","title":"Scriboora: Rethinking Human Pose Forecasting","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2601.19960","title":"Do we really need Self-Attention for Streaming Automatic Speech Recognition?","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2603.18031","title":"InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model","created":"2026-03-08","cited_by_count":0,"area":"ssm"},{"id":"2606.31112","title":"What Counts as an Error? Dual-Reference Benchmarking for Atypical ASR","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2606.31508","title":"Building an ASR Solution for Training and Assessing Children's Reading","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.12252","title":"DriftSE: Speech Enhancement with Generative Drifting","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.30846","title":"I-Parakeet: Integer-Only Conformer ASR on Mobile NPU","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}