{"total":151,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657,"area":null},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601,"area":null},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411,"area":null},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298,"area":null},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2203.07378","title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","created":"2022-03-14","cited_by_count":157,"area":null},{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148,"area":null},{"id":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126,"area":null},{"id":"2109.03264","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","created":"2021-09-07","cited_by_count":119,"area":null},{"id":"2305.10615","title":"ML-SUPERB: Multilingual Speech Universal PERformance Benchmark","created":"2023-05-18","cited_by_count":71,"area":null},{"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,"area":null},{"id":"2109.06870","title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","created":"2021-09-14","cited_by_count":68,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"area":null},{"id":"2202.03896","title":"Speech Emotion Recognition using Self-Supervised Features","created":"2022-02-07","cited_by_count":53,"area":null},{"id":"2110.06309","title":"Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition","created":"2021-10-12","cited_by_count":49,"area":null},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","cited_by_count":39,"area":null},{"id":"2303.18110","title":"The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR","created":"2023-03-31","cited_by_count":36,"area":null},{"id":"2203.16822","title":"How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications","created":"2022-03-31","cited_by_count":30,"area":null},{"id":"2204.03863","title":"Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning","created":"2022-04-08","cited_by_count":29,"area":null},{"id":"2408.06687","title":"Masked Image Modeling: A Survey","created":"2024-08-13","cited_by_count":29,"area":null},{"id":"2205.01086","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","created":"2022-05-02","cited_by_count":26,"area":null},{"id":"2210.08634","title":"SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning","created":"2022-10-16","cited_by_count":26,"area":null},{"id":"2312.15316","title":"Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue","created":"2023-12-23","cited_by_count":25,"area":null},{"id":"2108.12226","title":"Injecting Text in Self-Supervised Speech Pretraining","created":"2021-08-27","cited_by_count":24,"area":null},{"id":"2401.11943","title":"Benchmarking Large Multimodal Models against Common Corruptions","created":"2024-01-22","cited_by_count":24,"area":"lr"},{"id":"2403.07937","title":"Speech Robust Bench: A Robustness Benchmark For Speech Recognition","created":"2024-03-08","cited_by_count":21,"area":null},{"id":"2107.04082","title":"Improved Language Identification Through Cross-Lingual Self-Supervised Learning","created":"2021-07-08","cited_by_count":20,"area":null},{"id":"2110.07957","title":"Don't speak too fast: The impact of data bias on self-supervised speech models","created":"2021-10-15","cited_by_count":20,"area":null},{"id":"2210.13168","title":"Proficiency assessment of L2 spoken English using wav2vec 2.0","created":"2022-10-24","cited_by_count":20,"area":null},{"id":"2301.07295","title":"Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining","created":"2023-01-18","cited_by_count":18,"area":null},{"id":"2203.16104","title":"Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation","created":"2022-03-30","cited_by_count":17,"area":null},{"id":"2111.05948","title":"Scaling ASR Improves Zero and Few Shot Learning","created":"2021-11-10","cited_by_count":16,"area":null},{"id":"2110.07592","title":"DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances","created":"2021-10-14","cited_by_count":14,"area":null},{"id":"2302.14564","title":"Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition","created":"2023-02-28","cited_by_count":14,"area":null},{"id":"2204.00400","title":"Probing Speech Emotion Recognition Transformers for Linguistic Knowledge","created":"2022-04-01","cited_by_count":13,"area":null},{"id":"2110.03560","title":"Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0","created":"2021-10-07","cited_by_count":12,"area":null},{"id":"2112.07648","title":"On the Use of External Data for Spoken Named Entity Recognition","created":"2021-12-14","cited_by_count":12,"area":null},{"id":"2210.10191","title":"Simple and Effective Unsupervised Speech Translation","created":"2022-10-18","cited_by_count":12,"area":null},{"id":"2203.16965","title":"PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations","created":"2022-03-31","cited_by_count":11,"area":null},{"id":"2305.17733","title":"Investigating Pre-trained Audio Encoders in the Low-Resource Condition","created":"2023-05-28","cited_by_count":11,"area":null},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2206.09783","title":"Boosting Cross-Domain Speech Recognition with Self-Supervision","created":"2022-06-20","cited_by_count":10,"area":null},{"id":"2210.06324","title":"SQuId: Measuring Speech Naturalness in Many Languages","created":"2022-10-12","cited_by_count":10,"area":null},{"id":"2107.00594","title":"Pretext Tasks selection for multitask self-supervised speech representation learning","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2204.03219","title":"DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores","created":"2022-04-07","cited_by_count":7,"area":null},{"id":"2210.07978","title":"Improving generalizability of distilled self-supervised speech processing models under distorted settings","created":"2022-10-14","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":"2303.11131","title":"Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speech","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2311.09117","title":"R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces","created":"2023-11-15","cited_by_count":7,"area":null},{"id":"2409.14494","title":"CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments","created":"2024-09-13","cited_by_count":7,"area":null},{"id":"2303.07924","title":"Improving Accented Speech Recognition with Multi-Domain Training","created":"2023-03-14","cited_by_count":6,"area":null},{"id":"2401.14289","title":"Speech foundation models on intelligibility prediction for hearing-impaired listeners","created":"2024-01-24","cited_by_count":6,"area":null},{"id":"2111.14842","title":"Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?","created":"2021-11-29","cited_by_count":5,"area":null},{"id":"2211.01246","title":"data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup","created":"2022-11-02","cited_by_count":5,"area":"distill"},{"id":"2211.08989","title":"Avoid Overthinking in Self-Supervised Models for Speech Recognition","created":"2022-11-01","cited_by_count":5,"area":"lr"},{"id":"2305.07216","title":"Versatile audio-visual learning for emotion recognition","created":"2023-05-12","cited_by_count":5,"area":null},{"id":"2306.00410","title":"Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2309.17395","title":"AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition","created":"2023-09-29","cited_by_count":5,"area":null},{"id":"2210.15445","title":"Efficient Utilization of Large Pre-Trained Models for Low Resource ASR","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2303.12582","title":"AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages","created":"2023-03-22","cited_by_count":4,"area":null},{"id":"2305.05201","title":"Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models","created":"2023-05-09","cited_by_count":4,"area":null},{"id":"2305.08099","title":"Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations","created":"2023-05-14","cited_by_count":4,"area":null},{"id":"2306.15265","title":"Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition","created":"2023-06-27","cited_by_count":4,"area":null},{"id":"2405.13018","title":"Continued Pretraining for Domain Adaptation of Wav2vec2.0 in Automatic Speech Recognition for Elementary Math Classroom Settings","created":"2024-05-15","cited_by_count":4,"area":null},{"id":"2407.01143","title":"Are you sure? Analysing Uncertainty Quantification Approaches for Real-world Speech Emotion Recognition","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2411.12587","title":"Whisper Finetuning on Nepali Language","created":"2024-11-19","cited_by_count":4,"area":null},{"id":"2508.14130","title":"EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition","created":"2025-08-19","cited_by_count":4,"area":null},{"id":"2202.12719","title":"Ask2Mask: Guided Data Selection for Masked Speech Modeling","created":"2022-02-24","cited_by_count":3,"area":null},{"id":"2204.07272","title":"Automated speech tools for helping communities process restricted-access corpora for language revival efforts","created":"2022-04-15","cited_by_count":3,"area":null},{"id":"2207.14418","title":"Domain Specific Wav2vec 2.0 Fine-tuning For The SE&R 2022 Challenge","created":"2022-07-29","cited_by_count":3,"area":null},{"id":"2306.03773","title":"Some voices are too common: Building fair speech recognition systems using the Common Voice dataset","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2308.13345","title":"Decoupled Structure for Improved Adaptability of End-to-End Models","created":"2023-08-25","cited_by_count":3,"area":null},{"id":"2311.07037","title":"Phonological Level wav2vec2-based Mispronunciation Detection and Diagnosis Method","created":"2023-11-13","cited_by_count":3,"area":null},{"id":"2110.04863","title":"Injecting Text and Cross-lingual Supervision in Few-shot Learning from Self-Supervised Models","created":"2021-10-10","cited_by_count":2,"area":null},{"id":"2203.00648","title":"Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training","created":"2022-03-01","cited_by_count":2,"area":null},{"id":"2203.16973","title":"Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition","created":"2022-03-31","cited_by_count":2,"area":null},{"id":"2210.13030","title":"Self-supervised Rewiring of Pre-trained Speech Encoders: Towards Faster Fine-tuning with Less Labels in Speech Processing","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2303.00550","title":"Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation","created":"2023-03-01","cited_by_count":2,"area":"distill"},{"id":"2306.02972","title":"Simultaneous or Sequential Training? How Speech Representations Cooperate in a Multi-Task Self-Supervised Learning System","created":"2023-06-05","cited_by_count":2,"area":null},{"id":"2306.06086","title":"Developing Speech Processing Pipelines for Police Accountability","created":"2023-06-09","cited_by_count":2,"area":null},{"id":"2307.09744","title":"Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correction","created":"2023-07-19","cited_by_count":2,"area":null},{"id":"2309.15869","title":"Unsupervised Pre-Training for Vietnamese Automatic Speech Recognition in the HYKIST Project","created":"2023-09-26","cited_by_count":2,"area":null},{"id":"2310.10922","title":"Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2310.18450","title":"MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2312.07338","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2312.12783","title":"Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition","created":"2023-12-20","cited_by_count":2,"area":null},{"id":"2603.11378","title":"Continued Pretraining for Low-Resource Swahili ASR: Achieving State-of-the-Art Performance with Minimal Labeled Data","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2605.02715","title":"Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models","created":"2026-05-04","cited_by_count":2,"area":null},{"id":"2104.08806","title":"Best Practices for Noise-Based Augmentation to Improve the Performance of Deployable Speech-Based Emotion Recognition Systems","created":"2021-04-18","cited_by_count":1,"area":null},{"id":"2112.12522","title":"Multi-Variant Consistency based Self-supervised Learning for Robust Automatic Speech Recognition","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2209.11061","title":"Cross-domain Voice Activity Detection with Self-Supervised Representations","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2211.14700","title":"A novel multimodal dynamic fusion network for disfluency detection in spoken utterances","created":"2022-11-27","cited_by_count":1,"area":null},{"id":"2305.00619","title":"Self-supervised Activity Representation Learning with Incremental Data: An Empirical Study","created":"2023-05-01","cited_by_count":1,"area":null},{"id":"2306.01327","title":"Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2309.10077","title":"GAME: Generalized deep learning model towards multimodal data integration for early screening of adolescent mental disorders","created":"2023-09-18","cited_by_count":1,"area":null},{"id":"2312.13026","title":"FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning","created":"2023-12-20","cited_by_count":1,"area":null}],"next_cursor":"100"}