{"total":148,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727,"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":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197,"area":null},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180,"area":null},{"id":"2110.01900","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","created":"2021-10-05","cited_by_count":144,"area":null},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110,"area":null},{"id":"2202.01374","title":"mSLAM: Massively multilingual joint pre-training for speech and text","created":"2022-02-03","cited_by_count":108,"area":null},{"id":"2109.11680","title":"Simple and Effective Zero-shot Cross-lingual Phoneme Recognition","created":"2021-09-23","cited_by_count":79,"area":null},{"id":"2210.07321","title":"Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods","created":"2022-10-13","cited_by_count":79,"area":null},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"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":"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":"2209.15329","title":"SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data","created":"2022-09-30","cited_by_count":49,"area":null},{"id":"2204.02492","title":"Towards End-to-end Unsupervised Speech Recognition","created":"2022-04-05","cited_by_count":45,"area":null},{"id":"2305.17651","title":"DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models","created":"2023-05-28","cited_by_count":36,"area":null},{"id":"2210.11723","title":"Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech","created":"2022-10-21","cited_by_count":31,"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":"2210.00705","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","created":"2022-10-03","cited_by_count":29,"area":null},{"id":"2204.03417","title":"Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0","created":"2022-04-07","cited_by_count":27,"area":null},{"id":"2202.04774","title":"SHAS: Approaching optimal Segmentation for End-to-End Speech Translation","created":"2022-02-09","cited_by_count":26,"area":null},{"id":"2209.02842","title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio","created":"2022-09-06","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":"2410.04029","title":"SyllableLM: Learning Coarse Semantic Units for Speech Language Models","created":"2024-10-05","cited_by_count":24,"area":null},{"id":"2107.07402","title":"CLSRIL-23: Cross Lingual Speech Representations for Indic Languages","created":"2021-07-15","cited_by_count":22,"area":null},{"id":"2203.10752","title":"XTREME-S: Evaluating Cross-lingual Speech Representations","created":"2022-03-21","cited_by_count":22,"area":null},{"id":"2203.05383","title":"KSoF: The Kassel State of Fluency Dataset -- A Therapy Centered Dataset of Stuttering","created":"2022-03-10","cited_by_count":21,"area":null},{"id":"2204.05541","title":"Not always about you: Prioritizing community needs when developing endangered language technology","created":"2022-04-12","cited_by_count":21,"area":null},{"id":"2210.16043","title":"Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models","created":"2022-10-28","cited_by_count":21,"area":null},{"id":"2203.16773","title":"SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks","created":"2022-03-31","cited_by_count":19,"area":null},{"id":"2410.07168","title":"Sylber: Syllabic Embedding Representation of Speech from Raw Audio","created":"2024-10-09","cited_by_count":19,"area":null},{"id":"2406.02166","title":"Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision","created":"2024-06-04","cited_by_count":17,"area":null},{"id":"2112.08778","title":"Self-Supervised Learning for speech recognition with Intermediate layer supervision","created":"2021-12-16","cited_by_count":15,"area":null},{"id":"2402.01204","title":"A Survey on Self-Supervised Learning for Non-Sequential Tabular Data","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2106.04283","title":"NWT: Towards natural audio-to-video generation with representation learning","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2203.15796","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition","created":"2022-03-29","cited_by_count":14,"area":null},{"id":"2206.02211","title":"Variable-rate hierarchical CPC leads to acoustic unit discovery in speech","created":"2022-06-05","cited_by_count":13,"area":null},{"id":"2210.10027","title":"Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2305.17993","title":"Multi-Scale Attention for Audio Question Answering","created":"2023-05-29","cited_by_count":13,"area":null},{"id":"2204.02524","title":"Simple and Effective Unsupervised Speech Synthesis","created":"2022-04-06","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":"2308.15256","title":"Let There Be Sound: Reconstructing High Quality Speech from Silent Videos","created":"2023-08-29","cited_by_count":12,"area":null},{"id":"2401.13463","title":"SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering","created":"2024-01-24","cited_by_count":12,"area":null},{"id":"2111.06799","title":"Deciphering Speech: a Zero-Resource Approach to Cross-Lingual Transfer in ASR","created":"2021-11-12","cited_by_count":11,"area":null},{"id":"2203.15447","title":"Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus","created":"2022-03-29","cited_by_count":10,"area":null},{"id":"2203.01829","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2207.04356","title":"A Comparative Study of Self-supervised Speech Representation Based Voice Conversion","created":"2022-07-10","cited_by_count":9,"area":null},{"id":"2309.13860","title":"Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning","created":"2023-09-25","cited_by_count":9,"area":null},{"id":"2503.06273","title":"Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations","created":"2025-03-08","cited_by_count":9,"area":null},{"id":"2210.07189","title":"On Compressing Sequences for Self-Supervised Speech Models","created":"2022-10-13","cited_by_count":8,"area":null},{"id":"2309.15796","title":"Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition","created":"2023-09-26","cited_by_count":8,"area":null},{"id":"2407.17852","title":"Scaling A Simple Approach to Zero-Shot Speech Recognition","created":"2024-07-25","cited_by_count":8,"area":null},{"id":"2204.03855","title":"Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition","created":"2022-04-08","cited_by_count":7,"area":null},{"id":"2204.05148","title":"Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning","created":"2022-04-11","cited_by_count":7,"area":null},{"id":"2206.02512","title":"Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2206.12638","title":"Distilling a Pretrained Language Model to a Multilingual ASR Model","created":"2022-06-25","cited_by_count":7,"area":null},{"id":"2303.09278","title":"DistillW2V2: A Small and Streaming Wav2vec 2.0 Based ASR Model","created":"2023-03-16","cited_by_count":7,"area":"distill"},{"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":"2306.01108","title":"Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2306.08920","title":"Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation","created":"2023-06-15","cited_by_count":7,"area":null},{"id":"2307.10652","title":"Exploring the Landscape of Natural Language Processing Research","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2109.10107","title":"On the Difficulty of Segmenting Words with Attention","created":"2021-09-21","cited_by_count":6,"area":null},{"id":"2304.14514","title":"Understanding Shared Speech-Text Representations","created":"2023-04-27","cited_by_count":6,"area":null},{"id":"2305.18096","title":"Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target","created":"2023-05-29","cited_by_count":6,"area":null},{"id":"2106.04897","title":"Unsupervised Automatic Speech Recognition: A Review","created":"2021-06-09","cited_by_count":5,"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":"2201.11207","title":"Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition","created":"2022-01-26","cited_by_count":5,"area":null},{"id":"2203.11476","title":"Modeling speech recognition and synthesis simultaneously: Encoding and decoding lexical and sublexical semantic information into speech with no direct access to speech data","created":"2022-03-22","cited_by_count":5,"area":null},{"id":"2204.08226","title":"Empirical Evaluation and Theoretical Analysis for Representation Learning: A Survey","created":"2022-04-18","cited_by_count":5,"area":null},{"id":"2211.17196","title":"EURO: ESPnet Unsupervised ASR Open-source Toolkit","created":"2022-11-30","cited_by_count":5,"area":null},{"id":"2305.07455","title":"Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation","created":"2023-05-12","cited_by_count":5,"area":null},{"id":"2310.02382","title":"Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2401.01099","title":"Efficient Parallel Audio Generation using Group Masked Language Modeling","created":"2024-01-02","cited_by_count":5,"area":null},{"id":"2406.12209","title":"Interface Design for Self-Supervised Speech Models","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2211.00586","title":"T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5","created":"2022-11-01","cited_by_count":4,"area":null},{"id":"2303.01261","title":"ParrotTTS: Text-to-Speech synthesis by exploiting self-supervised representations","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2305.14580","title":"Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Person","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2306.04374","title":"Label Aware Speech Representation Learning For Language Identification","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2306.07926","title":"A Theory of Unsupervised Speech Recognition","created":"2023-06-09","cited_by_count":4,"area":null},{"id":"2402.03988","title":"REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR","created":"2024-02-06","cited_by_count":4,"area":null},{"id":"2409.10704","title":"Self-supervised Speech Models for Word-Level Stuttered Speech Detection","created":"2024-09-16","cited_by_count":4,"area":null},{"id":"2205.03026","title":"Hearing voices at the National Library -- a speech corpus and acoustic model for the Swedish language","created":"2022-05-06","cited_by_count":3,"area":null},{"id":"2206.05018","title":"Going Beyond the Cookie Theft Picture Test: Detecting Cognitive Impairments using Acoustic Features","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2211.03025","title":"Bridging Speech and Textual Pre-trained Models with Unsupervised ASR","created":"2022-11-06","cited_by_count":3,"area":null},{"id":"2211.08402","title":"Introducing Semantics into Speech Encoders","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2212.03232","title":"Learning the joint distribution of two sequences using little or no paired data","created":"2022-12-06","cited_by_count":3,"area":null},{"id":"2303.10160","title":"Visual Information Matters for ASR Error Correction","created":"2023-03-16","cited_by_count":3,"area":null},{"id":"2305.15405","title":"Textless Speech-to-Speech Translation With Limited Parallel Data","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2308.07121","title":"Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2311.18188","title":"Speech Understanding on Tiny Devices with A Learning Cache","created":"2023-11-30","cited_by_count":3,"area":null},{"id":"2312.09040","title":"STaR: Distilling Speech Temporal Relation for Lightweight Speech Self-Supervised Learning Models","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2402.09460","title":"Unsupervised learning based end-to-end delayless generative fixed-filter active noise control","created":"2024-02-08","cited_by_count":3,"area":null},{"id":"2403.03593","title":"Do You Trust Your Model? Emerging Malware Threats in the Deep Learning Ecosystem","created":"2024-03-06","cited_by_count":3,"area":null},{"id":"2404.02009","title":"Preuve de concept d'un bot vocal dialoguant en wolof","created":"2024-04-02","cited_by_count":3,"area":null},{"id":"2408.05554","title":"Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text","created":"2024-08-10","cited_by_count":3,"area":null}],"next_cursor":"100"}