{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-identification/papers/3","list_of":"/task/language-identification","task":"Language Identification","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":8,"rows_per_page":100,"rows":[201,300],"of":794,"counts":{"archive_papers_tagged":794,"with_a_code_link":143,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":794,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":4,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-identification","prev":"/task/language-identification/papers/2","next":"/task/language-identification/papers/4","papers":[{"url":null,"slug":"bilingual-streaming-asr-with-grapheme-units","title":"Bilingual Streaming ASR with Grapheme units and Auxiliary Monolingual Loss","date":"2023-08-11","arxiv_id":"2308.06327","repositories_listed":0,"syntology":null},{"url":null,"slug":"turkish-native-language-identification","title":"Turkish Native Language Identification","date":"2023-07-27","arxiv_id":"2307.14850","repositories_listed":0,"syntology":null},{"url":null,"slug":"masr-metadata-aware-speech-representation","title":"MASR: Multi-label Aware Speech Representation","date":"2023-07-20","arxiv_id":"2307.10982","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-speech-to-speech-translation","title":"Multilingual Speech-to-Speech Translation into Multiple Target Languages","date":"2023-07-17","arxiv_id":"2307.08655","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-spoken-dialect-identification-of","title":"Towards spoken dialect identification of Irish","date":"2023-07-14","arxiv_id":"2307.07436","repositories_listed":0,"syntology":null},{"url":null,"slug":"confidence-based-ensembles-of-end-to-end","title":"Confidence-based Ensembles of End-to-End Speech Recognition Models","date":"2023-06-27","arxiv_id":"2306.15824","repositories_listed":0,"syntology":null},{"url":null,"slug":"robertweet-a-bert-language-model-for-romanian","title":"RoBERTweet: A BERT Language Model for Romanian Tweets","date":"2023-06-11","arxiv_id":"2306.06598","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-language-identification-to-enhance","title":"Leveraging Language Identification to Enhance Code-Mixed Text Classification","date":"2023-06-08","arxiv_id":"2306.04964","repositories_listed":0,"syntology":null},{"url":null,"slug":"label-aware-speech-representation-learning","title":"Label Aware Speech Representation Learning For Language Identification","date":"2023-06-07","arxiv_id":"2306.04374","repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-yet-effective-code-switching-language","title":"Simple yet Effective Code-Switching Language Identification with Multitask Pre-Training and Transfer Learning","date":"2023-05-31","arxiv_id":"2305.19759","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-large-language-models-are-not","title":"Multilingual Large Language Models Are Not (Yet) Code-Switchers","date":"2023-05-23","arxiv_id":"2305.14235","repositories_listed":0,"syntology":null},{"url":null,"slug":"ml-superb-multilingual-speech-universal","title":"ML-SUPERB: Multilingual Speech Universal PERformance Benchmark","date":"2023-05-18","arxiv_id":"2305.10615","repositories_listed":0,"syntology":null},{"url":null,"slug":"lessons-learned-in-atco2-5000-hours-of-air","title":"Lessons Learned in ATCO2: 5000 hours of Air Traffic Control Communications for Robust Automatic Speech Recognition and Understanding","date":"2023-05-02","arxiv_id":"2305.01155","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmt-a-multilingual-and-multi-topic-indian","title":"MMT: A Multilingual and Multi-Topic Indian Social Media Dataset","date":"2023-04-02","arxiv_id":"2304.00634","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-unsupervised-and-supervised-learning","title":"Joint unsupervised and supervised learning for context-aware language identification","date":"2023-03-29","arxiv_id":"2303.16511","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-high-accuracy-multilingual-asr-with","title":"Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training","date":"2023-03-01","arxiv_id":"2303.00786","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmented-transformers-with-adaptive-n-grams","title":"Augmented Transformers with Adaptive n-grams Embedding for Multilingual Scene Text Recognition","date":"2023-02-28","arxiv_id":"2302.14261","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-identification-as-improvement-for","title":"Language identification as improvement for lip-based biometric visual systems","date":"2023-02-27","arxiv_id":"2302.13902","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-corpora-spoken-language-identification","title":"Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization","date":"2023-02-10","arxiv_id":"2302.05110","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-twitter-bert-approach-for-offensive","title":"A Twitter BERT Approach for Offensive Language Detection in Marathi","date":"2022-12-20","arxiv_id":"2212.10039","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overview-of-indian-spoken-language","title":"An Overview of Indian Spoken Language Recognition from Machine Learning Perspective","date":"2022-11-30","arxiv_id":"2212.03812","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-model-for-word-level","title":"Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts","date":"2022-11-26","arxiv_id":"2211.14459","repositories_listed":0,"syntology":null},{"url":null,"slug":"overview-of-the-hasoc-subtrack-at-fire-2022","title":"Overview of the HASOC Subtrack at FIRE 2022: Offensive Language Identification in Marathi","date":"2022-11-18","arxiv_id":"2211.10163","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-native-language-identification-with","title":"Scaling Native Language Identification with Transformer Adapters","date":"2022-11-18","arxiv_id":"2211.10117","repositories_listed":0,"syntology":null},{"url":null,"slug":"coli-machine-learning-approaches-for-code","title":"CoLI-Machine Learning Approaches for Code-mixed Language Identification at the Word Level in Kannada-English Texts","date":"2022-11-17","arxiv_id":"2211.09847","repositories_listed":0,"syntology":null},{"url":null,"slug":"accidental-learners-spoken-language","title":"Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models","date":"2022-11-09","arxiv_id":"2211.05103","repositories_listed":0,"syntology":null},{"url":null,"slug":"lamassu-streaming-language-agnostic","title":"LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers","date":"2022-11-05","arxiv_id":"2211.02809","repositories_listed":0,"syntology":null},{"url":null,"slug":"ambernet-a-compact-end-to-end-model-for","title":"A Compact End-to-End Model with Local and Global Context for Spoken Language Identification","date":"2022-10-27","arxiv_id":"2210.15781","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-networks-for-cross-domain-language","title":"Neural Networks for Cross-domain Language Identification. Phlyers @Vardial 2022","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ocwikidisc-a-corpus-of-wikipedia-talk-pages","title":"OcWikiDisc: a Corpus of Wikipedia Talk Pages in Occitan","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-end-to-end-multilingual-speech","title":"Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification","date":"2022-09-13","arxiv_id":"2209.06058","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-off-the-shelf-language","title":"Evaluation of Off-the-Shelf Language Identification Tools on Bulgarian Social Media Posts","date":"2022-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unravelling-interlanguage-facts-via","title":"Unravelling Interlanguage Facts via Explainable Machine Learning","date":"2022-08-02","arxiv_id":"2208.01468","repositories_listed":0,"syntology":null},{"url":null,"slug":"extending-rnn-t-based-speech-recognition","title":"Extending RNN-T-based speech recognition systems with emotion and language classification","date":"2022-07-28","arxiv_id":"2207.13965","repositories_listed":0,"syntology":null},{"url":null,"slug":"huqariq-a-multilingual-speech-corpus-of","title":"Huqariq: A Multilingual Speech Corpus of Native Languages of Peru for Speech Recognition","date":"2022-07-12","arxiv_id":"2207.05498","repositories_listed":0,"syntology":null},{"url":null,"slug":"techssn-at-semeval-2022-task-6-intended","title":"TechSSN at SemEval-2022 Task 6: Intended Sarcasm Detection using Transformer Models","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coswid-a-code-switching-identification-method","title":"CoSwID, a Code Switching Identification Method Suitable for Under-Resourced Languages","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-end-to-end-spoken","title":"Deep learning-based end-to-end spoken language identification system for domain-mismatched scenario","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dialects-identification-of-armenian-language","title":"Dialects Identification of Armenian Language","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"heli-ots-off-the-shelf-language-identifier","title":"HeLI-OTS, Off-the-shelf Language Identifier for Text","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"huqariq-a-multilingual-speech-corpus-of-1","title":"Huqariq: A Multilingual Speech Corpus of Native Languages of Peru forSpeech Recognition","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mhe-code-mixed-corpora-for-similar-language","title":"MHE: Code-Mixed Corpora for Similar Language Identification","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-dependencies-treebank-for-tatar","title":"Universal Dependencies Treebank for Tatar: Incorporating Intra-Word Code-Switching Information","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-synthesis-based-data-augmentation","title":"Adversarial synthesis based data-augmentation for code-switched spoken language identification","date":"2022-05-30","arxiv_id":"2205.15747","repositories_listed":0,"syntology":null},{"url":null,"slug":"modernizing-open-set-speech-language","title":"Modernizing Open-Set Speech Language Identification","date":"2022-05-20","arxiv_id":"2205.10397","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-spoken-language-identification-1","title":"Automatic Spoken Language Identification using a Time-Delay Neural Network","date":"2022-05-19","arxiv_id":"2205.09564","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretraining-approaches-for-spoken-language","title":"Pretraining Approaches for Spoken Language Recognition: TalTech Submission to the OLR 2021 Challenge","date":"2022-05-14","arxiv_id":"2205.07083","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-machine-translation-systems-for-the","title":"Building Machine Translation Systems for the Next Thousand Languages","date":"2022-05-09","arxiv_id":"2205.03983","repositories_listed":0,"syntology":null},{"url":"/paper/tugebic-a-turkish-german-bilingual-code","slug":"tugebic-a-turkish-german-bilingual-code","title":"TuGeBiC: A Turkish German Bilingual Code-Switching Corpus","date":"2022-05-02","arxiv_id":"2205.00868","repositories_listed":0,"syntology":null},{"url":null,"slug":"findings-of-the-shared-task-on-multi-task","title":"Findings of the Shared Task on Multi-task Learning in Dravidian Languages","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-speech-tools-for-helping","title":"Automated speech tools for helping communities process restricted-access corpora for language revival efforts","date":"2022-04-15","arxiv_id":"2204.07272","repositories_listed":0,"syntology":null},{"url":null,"slug":"transducer-based-language-embedding-for","title":"Transducer-based language embedding for spoken language identification","date":"2022-04-08","arxiv_id":"2204.03888","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-language-identification-of-accented","title":"Improving Language Identification of Accented Speech","date":"2022-03-31","arxiv_id":"2203.16972","repositories_listed":0,"syntology":null},{"url":null,"slug":"partial-coupling-of-optimal-transport-for","title":"Partial Coupling of Optimal Transport for Spoken Language Identification","date":"2022-03-31","arxiv_id":"2203.17036","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-switched-and-code-mixed-speech","title":"Code Switched and Code Mixed Speech Recognition for Indic languages","date":"2022-03-30","arxiv_id":"2203.16578","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-language-identification-for-celtic","title":"Automatic Language Identification for Celtic Texts","date":"2022-03-09","arxiv_id":"2203.04831","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-common-speech-analysis-engine","title":"Towards a Common Speech Analysis Engine","date":"2022-03-01","arxiv_id":"2203.00613","repositories_listed":0,"syntology":null},{"url":null,"slug":"calcs-2021-shared-task-machine-translation","title":"CALCS 2021 Shared Task: Machine Translation for Code-Switched Data","date":"2022-02-19","arxiv_id":"2202.09625","repositories_listed":0,"syntology":null},{"url":null,"slug":"hat5-hate-language-identification-using-text","title":"HaT5: Hate Language Identification using Text-to-Text Transfer Transformer","date":"2022-02-11","arxiv_id":"2202.05690","repositories_listed":0,"syntology":null},{"url":null,"slug":"translated-texts-under-the-lens-from-machine","title":"Translated Texts Under the Lens: From Machine Translation Detection to Source Language Identification","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cognitive-computing-to-optimize-it-services","title":"Cognitive Computing to Optimize IT Services","date":"2021-12-28","arxiv_id":"2201.02737","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-knowledge-in-end-to-end-automatic","title":"Integrating Knowledge in End-to-End Automatic Speech Recognition for Mandarin-English Code-Switching","date":"2021-12-19","arxiv_id":"2112.10202","repositories_listed":0,"syntology":null},{"url":null,"slug":"luc-at-comma-2021-shared-task-multilingual","title":"LUC at ComMA-2021 Shared Task: Multilingual Gender Biased and Communal Language Identification without using linguistic features","date":"2021-12-19","arxiv_id":"2112.10189","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-speech-representation-learning-via","title":"Robust Speech Representation Learning via Flow-based Embedding Regularization","date":"2021-12-07","arxiv_id":"2112.03454","repositories_listed":0,"syntology":null},{"url":null,"slug":"beware-haters-at-comma-icon-sequence-and","title":"Beware Haters at ComMA@ICON: Sequence and Ensemble Classifiers for Aggression, Gender Bias and Communal Bias Identification in Indian Languages","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bfcai-at-comma-icon-2021-support-vector","title":"BFCAI at ComMA@ICON 2021: Support Vector Machines for Multilingual Gender Biased and Communal Language Identification","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comma-icon-multilingual-gender-biased-and","title":"ComMA@ICON: Multilingual Gender Biased and Communal Language Identification Task at ICON-2021","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"delab-iiitsm-at-icon-2021-shared-task","title":"DELab@IIITSM at ICON-2021 Shared Task: Identification of Aggression and Biasness Using Decision Tree","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mucic-at-comma-icon-multilingual-gender","title":"MUCIC at ComMA@ICON: Multilingual Gender Biased and Communal Language Identification Using N-grams and Multilingual Sentence Encoders","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mum-at-comma-icon-multilingual-gender-biased","title":"MUM at ComMA@ICON: Multilingual Gender Biased and Communal Language Identification Using Supervised Learning Approaches","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-preference-aware-language","title":"Unsupervised Preference-Aware Language Identification","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-successful-shared-tasks-on","title":"Developing Successful Shared Tasks on Offensive Language Identification for Dravidian Languages","date":"2021-11-05","arxiv_id":"2111.03375","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-clustering-for-multilingual-named","title":"Language Clustering for Multilingual Named Entity Recognition","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"native-language-identification-and","title":"Native Language Identification and Reconstruction of Native Language Relationship Using Japanese Learner Corpus","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ceasing-hate-withmoh-hate-speech-detection-in","title":"Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language","date":"2021-10-18","arxiv_id":"2110.09393","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-the-score-shift-in-cross-lingual","title":"Tackling the Score Shift in Cross-Lingual Speaker Verification by Exploiting Language Information","date":"2021-10-18","arxiv_id":"2110.09150","repositories_listed":0,"syntology":null},{"url":null,"slug":"mandarin-english-code-switching-speech","title":"Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models","date":"2021-10-07","arxiv_id":"2110.03504","repositories_listed":0,"syntology":null},{"url":"/paper/is-attention-always-needed-a-case-study-on","slug":"is-attention-always-needed-a-case-study-on","title":"Is Attention always needed? A Case Study on Language Identification from Speech","date":"2021-10-05","arxiv_id":"2110.03427","repositories_listed":0,"syntology":null},{"url":"/paper/bigssl-exploring-the-frontier-of-large-scale","slug":"bigssl-exploring-the-frontier-of-large-scale","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","date":"2021-09-27","arxiv_id":"2109.13226","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-identification-with-a-reciprocal","title":"Language Identification with a Reciprocal Rank Classifier","date":"2021-09-20","arxiv_id":"2109.09862","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-futility-of-stilts-for-the-classification","title":"The futility of STILTs for the classification of lexical borrowings in Spanish","date":"2021-09-17","arxiv_id":"2109.08607","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-personality-aware-language","title":"Unsupervised Personality-Aware Language Identification","date":"2021-09-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fbert-a-neural-transformer-for-identifying","title":"FBERT: A Neural Transformer for Identifying Offensive Content","date":"2021-09-10","arxiv_id":"2109.05074","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-pre-trained-transformer-and-cnn-model-with","title":"A Pre-trained Transformer and CNN Model with Joint Language ID and Part-of-Speech Tagging for Code-Mixed Social-Media Text","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"corpus-creation-and-language-identification","title":"Corpus Creation and Language Identification in Low-Resource Code-Mixed Telugu-English Text","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fiction-in-russian-translation-a","title":"Fiction in Russian Translation: A Translationese Study","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dual-decoder-conformer-for-multilingual","title":"A Dual-Decoder Conformer for Multilingual Speech Recognition","date":"2021-08-22","arxiv_id":"2109.03277","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyn-asr-compact-multilingual-speech","title":"Dyn-ASR: Compact, Multilingual Speech Recognition via Spoken Language and Accent Identification","date":"2021-08-04","arxiv_id":"2108.02034","repositories_listed":0,"syntology":null},{"url":"/paper/olr-2021-challenge-datasets-rules-and","slug":"olr-2021-challenge-datasets-rules-and","title":"OLR 2021 Challenge: Datasets, Rules and Baselines","date":"2021-07-23","arxiv_id":"2107.11113","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-language-identification-through","title":"Improved Language Identification Through Cross-Lingual Self-Supervised Learning","date":"2021-07-08","arxiv_id":"2107.04082","repositories_listed":0,"syntology":null},{"url":null,"slug":"oriental-language-recognition-olr-2020","title":"Oriental Language Recognition (OLR) 2020: Summary and Analysis","date":"2021-07-05","arxiv_id":"2107.05365","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-identification-of-hindi-english","title":"Language Identification of Hindi-English tweets using code-mixed BERT","date":"2021-07-02","arxiv_id":"2107.01202","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-and-efficient-probabilistic-language","title":"A Simple and Efficient Probabilistic Language model for Code-Mixed Text","date":"2021-06-29","arxiv_id":"2106.15102","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-lexicons-for-hindi-english","title":"Language Lexicons for Hindi-English Multilingual Text Processing","date":"2021-06-29","arxiv_id":"2106.15105","repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-based-multi-task-model-for-country-and","title":"BERT-based Multi-Task Model for Country and Province Level Modern Standard Arabic and Dialectal Arabic Identification","date":"2021-06-23","arxiv_id":"2106.12495","repositories_listed":0,"syntology":null},{"url":null,"slug":"sigtyp-2021-shared-task-robust-spoken","title":"SIGTYP 2021 Shared Task: Robust Spoken Language Identification","date":"2021-06-07","arxiv_id":"2106.03895","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-and-negative-evidence-for","title":"Active learning and negative evidence for language identification","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"anlirika-an-lstm-cnn-flow-twister-for-spoken","title":"Anlirika: An LSTM–CNN Flow Twister for Spoken Language Identification","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-filtering-using-cross-lingual-word","title":"Data Filtering using Cross-Lingual Word Embeddings","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-id-prediction-from-speech-using-self-1","title":"Language ID Prediction from Speech Using Self-Attentive Pooling","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"f8a10240eed2e074dbf0d16c6ad00605073cd74a151be67e289d11782c358fee","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}