{"list":"other","total":63,"rows":[{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"1912.00582","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","created":"2019-12-02","cited_by_count":564},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"1408.3456","title":"SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation","created":"2014-08-15","cited_by_count":172},{"id":"2107.05604","title":"Direct speech-to-speech translation with discrete units","created":"2021-07-12","cited_by_count":149},{"id":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126},{"id":"2112.08352","title":"Textless Speech-to-Speech Translation on Real Data","created":"2021-12-15","cited_by_count":121},{"id":"2109.03264","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","created":"2021-09-07","cited_by_count":119},{"id":"1904.06037","title":"Direct speech-to-speech translation with a sequence-to-sequence model","created":"2019-04-12","cited_by_count":118},{"id":"2002.02848","title":"Unsupervised pretraining transfers well across languages","created":"2020-02-07","cited_by_count":101},{"id":"2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","created":"2020-11-23","cited_by_count":101},{"id":"1901.08810","title":"Unsupervised speech representation learning using WaveNet autoencoders","created":"2019-01-25","cited_by_count":90},{"id":"2203.16691","title":"MAE-AST: Masked Autoencoding Audio Spectrogram Transformer","created":"2022-03-30","cited_by_count":82},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77},{"id":"2204.09224","title":"ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers","created":"2022-04-20","cited_by_count":74},{"id":"1607.08723","title":"Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner","created":"2016-07-29","cited_by_count":68},{"id":"2007.00991","title":"Data Augmenting Contrastive Learning of Speech Representations in the Time Domain","created":"2020-07-02","cited_by_count":63},{"id":"2005.09409","title":"Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge","created":"2020-05-19","cited_by_count":55},{"id":"1803.08976","title":"Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech","created":"2018-03-23","cited_by_count":52},{"id":"2104.14700","title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","created":"2021-04-29","cited_by_count":47},{"id":"1712.04313","title":"The Zero Resource Speech Challenge 2017","created":"2017-12-12","cited_by_count":45},{"id":"1608.00869","title":"SimVerb-3500: A Large-Scale Evaluation Set of Verb Similarity","created":"2016-08-02","cited_by_count":44},{"id":"2010.05967","title":"The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units","created":"2020-10-12","cited_by_count":39},{"id":"1904.11469","title":"The Zero Resource Speech Challenge 2019: TTS without T","created":"2019-04-25","cited_by_count":38},{"id":"1702.01991","title":"Representations of language in a model of visually grounded speech signal","created":"2017-02-07","cited_by_count":37},{"id":"2203.16193","title":"Probing phoneme, language and speaker information in unsupervised speech representations","created":"2022-03-30","cited_by_count":33},{"id":"2106.02170","title":"Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation","created":"2021-06-03","cited_by_count":32},{"id":"1703.08135","title":"An embedded segmental K-means model for unsupervised segmentation and clustering of speech","created":"2017-03-23","cited_by_count":31},{"id":"2205.15819","title":"Do self-supervised speech models develop human-like perception biases?","created":"2022-05-31","cited_by_count":28},{"id":"1606.06950","title":"A segmental framework for fully-unsupervised large-vocabulary speech recognition","created":"2016-06-22","cited_by_count":27},{"id":"1910.00795","title":"Speech-to-speech Translation between Untranscribed Unknown Languages","created":"2019-10-02","cited_by_count":27},{"id":"2108.00917","title":"Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing","created":"2021-08-02","cited_by_count":26},{"id":"2202.03543","title":"Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling","created":"2022-02-07","cited_by_count":25},{"id":"2202.11929","title":"Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring","created":"2022-02-24","cited_by_count":24},{"id":"2203.05936","title":"Are discrete units necessary for Spoken Language Modeling?","created":"2022-03-11","cited_by_count":24},{"id":"2005.11676","title":"Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge","created":"2020-05-24","cited_by_count":21},{"id":"2007.13542","title":"Evaluating the reliability of acoustic speech embeddings","created":"2020-07-27","cited_by_count":21},{"id":"1904.07556","title":"Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks","created":"2019-04-16","cited_by_count":20},{"id":"2110.15909","title":"Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words","created":"2021-10-29","cited_by_count":18},{"id":"2008.00731","title":"Unsupervised Discovery of Recurring Speech Patterns Using Probabilistic Adaptive Metrics","created":"2020-08-03","cited_by_count":16},{"id":"2110.02345","title":"Unsupervised Speech Segmentation and Variable Rate Representation Learning using Segmental Contrastive Predictive Coding","created":"2021-10-05","cited_by_count":14},{"id":"1905.11563","title":"Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion","created":"2019-05-28","cited_by_count":12},{"id":"2007.13033","title":"Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery","created":"2020-07-26","cited_by_count":12},{"id":"2011.03115","title":"A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery","created":"2020-11-04","cited_by_count":9},{"id":"2203.01829","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","created":"2022-03-01","cited_by_count":9},{"id":"2008.06892","title":"Unsupervised Acoustic Unit Representation Learning for Voice Conversion using WaveNet Auto-encoders","created":"2020-08-16","cited_by_count":8},{"id":"2106.11603","title":"Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw","created":"2021-06-22","cited_by_count":7},{"id":"2107.05899","title":"Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021","created":"2021-07-13","cited_by_count":7},{"id":"2010.05961","title":"Perceptimatic: A human speech perception benchmark for unsupervised subword modelling","created":"2020-10-12","cited_by_count":6},{"id":"2107.06546","title":"ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition","created":"2021-07-14","cited_by_count":6},{"id":"1906.07234","title":"Combining Adversarial Training and Disentangled Speech Representation for Robust Zero-Resource Subword Modeling","created":"2019-06-17","cited_by_count":5},{"id":"1802.05092","title":"Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the \"Speaking Rosetta\" JSALT 2017 Workshop","created":"2018-02-14","cited_by_count":4},{"id":"2005.05487","title":"Exploring TTS without T Using Biologically/Psychologically Motivated Neural Network Modules (ZeroSpeech 2020)","created":"2020-05-11","cited_by_count":2},{"id":"2205.15823","title":"Predicting non-native speech perception using the Perceptual Assimilation Model and state-of-the-art acoustic models","created":"2022-05-31","cited_by_count":2},{"id":"2006.04372","title":"Zero resource speech synthesis using transcripts derived from perceptual acoustic units","created":"2020-06-08","cited_by_count":1},{"id":"2009.04983","title":"Exploration of End-to-end Synthesisers forZero Resource Speech Challenge 2020","created":"2020-09-10","cited_by_count":1}],"next_cursor":null}