{"list":"other","total":51,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"1609.06773","title":"Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning","created":"2016-09-21","cited_by_count":257},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176},{"id":"1906.01815","title":"Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)","created":"2019-06-05","cited_by_count":174},{"id":"2307.11795","title":"Prompting Large Language Models with Speech Recognition Abilities","created":"2023-07-21","cited_by_count":140},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101},{"id":"2104.02133","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","created":"2021-04-05","cited_by_count":83},{"id":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80},{"id":"2309.07937","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","created":"2023-09-14","cited_by_count":72},{"id":"2207.01063","title":"DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech","created":"2022-07-03","cited_by_count":69},{"id":"2109.09138","title":"Multi-Task Learning in Natural Language Processing: An Overview","created":"2021-09-19","cited_by_count":62},{"id":"2104.14830","title":"Scaling End-to-End Models for Large-Scale Multilingual ASR","created":"2021-04-30","cited_by_count":61},{"id":"2102.05889","title":"ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech","created":"2021-02-11","cited_by_count":58},{"id":"1802.06655","title":"Tied Multitask Learning for Neural Speech Translation","created":"2018-02-19","cited_by_count":54},{"id":"2111.14706","title":"ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet","created":"2021-11-29","cited_by_count":53},{"id":"2305.11095","title":"Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization","created":"2023-05-18","cited_by_count":43},{"id":"1412.7489","title":"A Unified Perspective on Multi-Domain and Multi-Task Learning","created":"2014-12-23","cited_by_count":33},{"id":"2110.04621","title":"Universal Paralinguistic Speech Representations Using Self-Supervised Conformers","created":"2021-10-09","cited_by_count":32},{"id":"2303.00733","title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","created":"2023-03-01","cited_by_count":32},{"id":"1704.01631","title":"Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition","created":"2017-04-05","cited_by_count":29},{"id":"2206.02119","title":"A Multimodal Corpus for Emotion Recognition in Sarcasm","created":"2022-06-05","cited_by_count":29},{"id":"1810.12735","title":"Spoken Language Understanding on the Edge","created":"2018-10-30","cited_by_count":27},{"id":"2203.15863","title":"WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models","created":"2022-03-29","cited_by_count":26},{"id":"2101.04792","title":"Learning Efficient Representations for Keyword Spotting with Triplet Loss","created":"2021-01-12","cited_by_count":24},{"id":"2011.09044","title":"Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding","created":"2020-11-18","cited_by_count":23},{"id":"2207.10643","title":"STOP: A dataset for Spoken Task Oriented Semantic Parsing","created":"2022-06-29","cited_by_count":22},{"id":"1812.06081","title":"A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization","created":"2018-12-14","cited_by_count":20},{"id":"2109.13510","title":"VoxCeleb Enrichment for Age and Gender Recognition","created":"2021-09-28","cited_by_count":20},{"id":"2005.07973","title":"AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition","created":"2020-05-16","cited_by_count":19},{"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},{"id":"2008.01994","title":"Improving End-to-End Speech-to-Intent Classification with Reptile","created":"2020-08-05","cited_by_count":17},{"id":"2010.13886","title":"MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection","created":"2020-10-26","cited_by_count":12},{"id":"1909.01720","title":"Different Absorption from the Same Sharing: Sifted Multi-task Learning for Fake News Detection","created":"2019-09-04","cited_by_count":11},{"id":"2210.15734","title":"Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models","created":"2022-10-27","cited_by_count":10},{"id":"2001.10816","title":"Multi-task Learning for Speaker Verification and Voice Trigger Detection","created":"2020-01-26","cited_by_count":9},{"id":"2309.09843","title":"Instruction-Following Speech Recognition","created":"2023-09-18","cited_by_count":7},{"id":"2207.03852","title":"Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription","created":"2022-07-08","cited_by_count":6},{"id":"2305.01620","title":"A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing toward STOP Quality Challenge","created":"2023-05-02","cited_by_count":5},{"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}],"next_cursor":null}