{"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/automatic-speech-recognition-2/papers/28","list_of":"/task/automatic-speech-recognition-2","task":"Automatic Speech Recognition","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":28,"pages_in_order":32,"rows_per_page":100,"rows":[2701,2800],"of":3174,"counts":{"archive_papers_tagged":3174,"with_a_code_link":677,"where_syntology_ran_a_sample":79,"not_listed_spam_title":0,"listed":3174,"listed_where_code_ran":79,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":62,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":62,"listed_every_run_a_failure_of_syntologys_instrument":17,"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/automatic-speech-recognition-2","prev":"/task/automatic-speech-recognition-2/papers/27","next":"/task/automatic-speech-recognition-2/papers/29","papers":[{"url":null,"slug":"191013215","title":"Transformer-based Cascaded Multimodal Speech Translation","date":"2019-10-29","arxiv_id":"1910.13215","repositories_listed":0,"syntology":null},{"url":null,"slug":"191013296","title":"Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation","date":"2019-10-29","arxiv_id":"1910.13296","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-speech-enhancement-of-publicly-available","title":"Does Speech enhancement of publicly available data help build robust Speech Recognition Systems?","date":"2019-10-29","arxiv_id":"1910.13488","repositories_listed":0,"syntology":null},{"url":null,"slug":"dfsmn-san-with-persistent-memory-model-for","title":"DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition","date":"2019-10-28","arxiv_id":"1910.13282","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pre-traing-for-sequence-to","title":"Unsupervised pre-training for sequence to sequence speech recognition","date":"2019-10-28","arxiv_id":"1910.12418","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-learning-for-end-to-end-low-resource","title":"Meta Learning for End-to-End Low-Resource Speech Recognition","date":"2019-10-26","arxiv_id":"1910.12094","repositories_listed":0,"syntology":null},{"url":null,"slug":"l2rs-a-learning-to-rescore-mechanism-for","title":"L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition","date":"2019-10-25","arxiv_id":"1910.11496","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-online-end-to-end-transformer","title":"Towards Online End-to-end Transformer Automatic Speech Recognition","date":"2019-10-25","arxiv_id":"1910.11871","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-in-deep-reinforcement-learning","title":"Pre-training in Deep Reinforcement Learning for Automatic Speech Recognition","date":"2019-10-24","arxiv_id":"1910.11256","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognizing-long-form-speech-using-streaming","title":"Recognizing long-form speech using streaming end-to-end models","date":"2019-10-24","arxiv_id":"1910.11455","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-practical-two-stage-training-strategy-for","title":"A practical two-stage training strategy for multi-stream end-to-end speech recognition","date":"2019-10-23","arxiv_id":"1910.10671","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-asr-pretraining-for-low-resource","title":"Analyzing ASR pretraining for low-resource speech-to-text translation","date":"2019-10-23","arxiv_id":"1910.10762","repositories_listed":0,"syntology":null},{"url":null,"slug":"correction-of-automatic-speech-recognition","title":"Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model","date":"2019-10-23","arxiv_id":"1910.10697","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-online-spoken-language","title":"RNN based Incremental Online Spoken Language Understanding","date":"2019-10-23","arxiv_id":"1910.10287","repositories_listed":0,"syntology":null},{"url":null,"slug":"g2g-tts-driven-pronunciation-learning-for","title":"G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR","date":"2019-10-22","arxiv_id":"1910.12612","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-neural-machine-translation-for-clean","title":"Robust Neural Machine Translation for Clean and Noisy Speech Transcripts","date":"2019-10-22","arxiv_id":"1910.10238","repositories_listed":0,"syntology":null},{"url":null,"slug":"perceptual-speech-enhancement-via-generative","title":"AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks","date":"2019-10-21","arxiv_id":"1910.12620","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-serket-development-of-integrative","title":"Neuro-SERKET: Development of Integrative Cognitive System through the Composition of Deep Probabilistic Generative Models","date":"2019-10-20","arxiv_id":"1910.08918","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-talker-mvdr-beamforming-based-on","title":"Multi-Talker MVDR Beamforming Based on Extended Complex Gaussian Mixture Model","date":"2019-10-17","arxiv_id":"1910.07753","repositories_listed":0,"syntology":null},{"url":null,"slug":"lead2gold-towards-exploiting-the-full","title":"Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition","date":"2019-10-16","arxiv_id":"1910.07323","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-asr-with-contextual-block","title":"Transformer ASR with Contextual Block Processing","date":"2019-10-16","arxiv_id":"1910.07204","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-large-receptive-field-convolutional","title":"Analyzing Large Receptive Field Convolutional Networks for Distant Speech Recognition","date":"2019-10-15","arxiv_id":"1910.07047","repositories_listed":0,"syntology":null},{"url":null,"slug":"vais-asr-building-a-conversational-speech","title":"VAIS ASR: Building a conversational speech recognition system using language model combination","date":"2019-10-12","arxiv_id":"1910.05603","repositories_listed":0,"syntology":null},{"url":null,"slug":"hear-no-evil-see-kenansville-efficient-and","title":"Hear \"No Evil\", See \"Kenansville\": Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systems","date":"2019-10-11","arxiv_id":"1910.05262","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-by-example-on-device-keyword-spotting","title":"Query-by-example on-device keyword spotting","date":"2019-10-11","arxiv_id":"1910.05171","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-to-many-multilingual-end-to-end-speech","title":"One-To-Many Multilingual End-to-end Speech Translation","date":"2019-10-08","arxiv_id":"1910.03320","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-case-study-on-combining-asr-and-visual","title":"A Case Study on Combining ASR and Visual Features for Generating Instructional Video Captions","date":"2019-10-07","arxiv_id":"1910.02930","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-a-framenet-semantic-parser-for","title":"Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning","date":"2019-10-07","arxiv_id":"1910.02734","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-confidence-in-sequence-to-sequence","title":"Modeling Confidence in Sequence-to-Sequence Models","date":"2019-10-04","arxiv_id":"1910.01859","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-zero-inflated-quality-estimation-model","title":"Neural Zero-Inflated Quality Estimation Model For Automatic Speech Recognition System","date":"2019-10-03","arxiv_id":"1910.01289","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-senones-to-chenones-tied-context","title":"From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition","date":"2019-10-02","arxiv_id":"1910.01493","repositories_listed":0,"syntology":null},{"url":null,"slug":"shi-yong-sheng-cheng-dui-kang-wang-lu-yu","title":"使用生成對抗網路於強健式自動語音辨識的應用(Exploiting Generative Adversarial Network for Robustness Automatic Speech Recognition)","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-code-switching-asr-for-low","title":"End-to-End Code-Switching ASR for Low-Resourced Language Pairs","date":"2019-09-27","arxiv_id":"1909.12681","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-data-barrier-towards-robust","title":"Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training","date":"2019-09-25","arxiv_id":"1909.11430","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-robust-audio-adversarial-examples","title":"Generating Robust Audio Adversarial Examples using Iterative Proportional Clipping","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-training-techniques-for-online","title":"Improved Training Techniques for Online Neural Machine Translation","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-semantics-from-speech-through","title":"Understanding Semantics from Speech Through Pre-training","date":"2019-09-24","arxiv_id":"1909.10924","repositories_listed":0,"syntology":null},{"url":null,"slug":"190909993","title":"Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR","date":"2019-09-22","arxiv_id":"1909.09993","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-switched-language-models-using-neural","title":"Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences","date":"2019-09-18","arxiv_id":"1909.08582","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-speech-recognition-and-speaker","title":"Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models","date":"2019-09-17","arxiv_id":"1909.08103","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-investigation-into-on-device","title":"An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models","date":"2019-09-14","arxiv_id":"1909.06678","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-source-channel-and-attention","title":"Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition","date":"2019-09-14","arxiv_id":"1909.06614","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-out-of-task-data-for-end-to-end","title":"Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade","date":"2019-09-14","arxiv_id":"1909.06515","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-multilingual-speech-recognition","title":"Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model","date":"2019-09-11","arxiv_id":"1909.05330","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-based-modeling-of-phonetic","title":"Neural Network-Based Modeling of Phonetic Durations","date":"2019-09-06","arxiv_id":"1909.03030","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialect-specific-models-for-automatic-speech","title":"Dialect-Specific Models for Automatic Speech Recognition of African American Vernacular English","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"human-informed-speakers-and-interpreters","title":"Human-Informed Speakers and Interpreters Analysis in the WAW Corpus and an Automatic Method for Calculating Interpreters' D\\'ecalage","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"motivations-challenges-and-perspectives-for","title":"Motivations, challenges, and perspectives for the development of an Automatic Speech Recognition System for the under-resourced Ngiemboon Language","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-language-model-for-tunisian-dialect","title":"Semantic Language Model for Tunisian Dialect","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-accurate-text-verbalization-for-asr","title":"Towards Accurate Text Verbalization for ASR Based on Audio Alignment","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deploying-technology-to-save-endangered","title":"Deploying Technology to Save Endangered Languages","date":"2019-08-23","arxiv_id":"1908.08971","repositories_listed":0,"syntology":null},{"url":null,"slug":"gender-representation-in-french-broadcast","title":"Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance","date":"2019-08-23","arxiv_id":"1908.08717","repositories_listed":0,"syntology":null},{"url":null,"slug":"190807888","title":"Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition","date":"2019-08-21","arxiv_id":"1908.07888","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-staged-acoustic-modeling-adaption-for","title":"Two-Staged Acoustic Modeling Adaption for Robust Speech Recognition by the Example of German Oral History Interviews","date":"2019-08-19","arxiv_id":"1908.06709","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-multi-speaker-speech-recognition","title":"End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning","date":"2019-08-13","arxiv_id":"1908.04737","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-stemming-based-language-model","title":"Unsupervised Stemming based Language Model for Telugu Broadcast News Transcription","date":"2019-08-10","arxiv_id":"1908.03734","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-cross-lingual-speaker-and-phonetic","title":"Exploiting Cross-Lingual Speaker and Phonetic Diversity for Unsupervised Subword Modeling","date":"2019-08-09","arxiv_id":"1908.03538","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-semi-supervised-training-through-a","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","date":"2019-08-08","arxiv_id":"1908.05227","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-noisy-inputs-for-question","title":"Mitigating Noisy Inputs for Question Answering","date":"2019-08-08","arxiv_id":"1908.02914","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-accurate-capitalization-and","title":"Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging","date":"2019-08-07","arxiv_id":"1908.02404","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-text-independent-speaker","title":"An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network","date":"2019-08-06","arxiv_id":"1908.02612","repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-speech-recognition-with-htk","title":"Practical Speech Recognition with HTK","date":"2019-08-06","arxiv_id":"1908.02119","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-over-the-air-adversarial-examples","title":"Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems","date":"2019-08-05","arxiv_id":"1908.01551","repositories_listed":0,"syntology":null},{"url":null,"slug":"v2s-attack-building-dnn-based-voice","title":"V2S attack: building DNN-based voice conversion from automatic speaker verification","date":"2019-08-05","arxiv_id":"1908.01454","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-speech-test-set-of-practice-business","title":"A Speech Test Set of Practice Business Presentations with Additional Relevant Texts","date":"2019-08-02","arxiv_id":"1908.00916","repositories_listed":0,"syntology":null},{"url":null,"slug":"dutongchuan-context-aware-translation-model","title":"DuTongChuan: Context-aware Translation Model for Simultaneous Interpreting","date":"2019-07-30","arxiv_id":"1907.12984","repositories_listed":0,"syntology":null},{"url":null,"slug":"correlation-distance-skip-connection","title":"Correlation Distance Skip Connection Denoising Autoencoder (CDSK-DAE) for Speech Feature Enhancement","date":"2019-07-26","arxiv_id":"1907.11361","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-sequence-to-sequence-voice","title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","date":"2019-07-15","arxiv_id":"1907.07769","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-target-set-reduction-for-end-to","title":"Investigating Target Set Reduction for End-to-End Speech Recognition of Hindi-English Code-Switching Data","date":"2019-07-15","arxiv_id":"1907.08293","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-highly-efficient-distributed-deep-learning","title":"A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition","date":"2019-07-10","arxiv_id":"1907.05701","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-model-optimization-based-on","title":"Acoustic Model Optimization Based On Evolutionary Stochastic Gradient Descent with Anchors for Automatic Speech Recognition","date":"2019-07-10","arxiv_id":"1907.04882","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-mixed-bandwidth-deep-neural","title":"Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition","date":"2019-07-10","arxiv_id":"1907.04887","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-speech-recognition-and-speaker","title":"Joint Speech Recognition and Speaker Diarization via Sequence Transduction","date":"2019-07-09","arxiv_id":"1907.05337","repositories_listed":0,"syntology":null},{"url":null,"slug":"teach-an-all-rounder-with-experts-in","title":"Teach an all-rounder with experts in different domains","date":"2019-07-09","arxiv_id":"1907.05698","repositories_listed":0,"syntology":null},{"url":null,"slug":"shrinkml-end-to-end-asr-model-compression","title":"ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning","date":"2019-07-08","arxiv_id":"1907.03540","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-low-resource-somali-speech","title":"Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training","date":"2019-07-06","arxiv_id":"1907.03064","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-speech-recognition-with-high-frame","title":"End-to-End Speech Recognition with High-Frame-Rate Features Extraction","date":"2019-07-03","arxiv_id":"1907.01957","repositories_listed":0,"syntology":null},{"url":"/paper/kite-automatic-speech-recognition-for","slug":"kite-automatic-speech-recognition-for","title":"Kite: Automatic speech recognition for unmanned aerial vehicles","date":"2019-07-02","arxiv_id":"1907.01195","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-dirichlet-allocation-based-acoustic","title":"Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition","date":"2019-07-02","arxiv_id":"1907.01302","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-multi-corpora-neural-language-models","title":"Scalable Multi Corpora Neural Language Models for ASR","date":"2019-07-02","arxiv_id":"1907.01677","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-cross-language-intelligibility","title":"Automated Cross-language Intelligibility Analysis of Parkinson's Disease Patients Using Speech Recognition Technologies","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-lattice-free-and-lattice-based","title":"Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR","date":"2019-07-01","arxiv_id":"1907.01409","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-utility-of-visual-context-in","title":"Analyzing Utility of Visual Context in Multimodal Speech Recognition Under Noisy Conditions","date":"2019-06-30","arxiv_id":"1907.00477","repositories_listed":0,"syntology":null},{"url":null,"slug":"auxiliary-interference-speaker-loss-for","title":"Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition","date":"2019-06-26","arxiv_id":"1906.10876","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-size-does-not-fit-all-quantifying-and","title":"One Size Does Not Fit All: Quantifying and Exposing the Accuracy-Latency Trade-off in Machine Learning Cloud Service APIs via Tolerance Tiers","date":"2019-06-26","arxiv_id":"1906.11307","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-span-acoustic-modelling-using-raw","title":"Multi-Span Acoustic Modelling using Raw Waveform Signals","date":"2019-06-21","arxiv_id":"1906.11047","repositories_listed":0,"syntology":null},{"url":null,"slug":"phoneme-based-contextualization-for-cross","title":"Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models","date":"2019-06-21","arxiv_id":"1906.09292","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-switching-detection-using-asr-generated","title":"Code-Switching Detection Using ASR-Generated Language Posteriors","date":"2019-06-19","arxiv_id":"1906.08003","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-graph-decoding-for-code-switching-asr","title":"Multi-Graph Decoding for Code-Switching ASR","date":"2019-06-18","arxiv_id":"1906.07523","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-speech-recognition-with-no-speech","title":"Advancing Speech Recognition With No Speech Or With Noisy Speech","date":"2019-06-17","arxiv_id":"1906.08871","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-training-for-multilingual","title":"Adversarial Training for Multilingual Acoustic Modeling","date":"2019-06-17","arxiv_id":"1906.07093","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stream-end-to-end-speech-recognition","title":"Multi-Stream End-to-End Speech Recognition","date":"2019-06-17","arxiv_id":"1906.08041","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-to-h-space-encoder-for-speech","title":"Real to H-space Encoder for Speech Recognition","date":"2019-06-17","arxiv_id":"1906.08043","repositories_listed":0,"syntology":null},{"url":null,"slug":"cumulative-adaptation-for-blstm-acoustic","title":"Cumulative Adaptation for BLSTM Acoustic Models","date":"2019-06-14","arxiv_id":"1906.06207","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-bidirectional-transformer-for","title":"Learning Video Representations using Contrastive Bidirectional Transformer","date":"2019-06-13","arxiv_id":"1906.05743","repositories_listed":0,"syntology":null},{"url":null,"slug":"lattice-transformer-for-speech-translation","title":"Lattice Transformer for Speech Translation","date":"2019-06-13","arxiv_id":"1906.05551","repositories_listed":0,"syntology":null},{"url":null,"slug":"190600579","title":"Listening while Speaking and Visualizing: Improving ASR through Multimodal Chain","date":"2019-06-03","arxiv_id":"1906.00579","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-user-study-to-compare-two-conversational","title":"A user study to compare two conversational assistants designed for people with hearing impairments","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-de-identification-a-new-entity-1","title":"Audio De-identification - a New Entity Recognition Task","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/must-c-a-multilingual-speech-translation","slug":"must-c-a-multilingual-speech-translation","title":"MuST-C: a Multilingual Speech Translation Corpus","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"cd21dcdd2fe750f5cb2c9cdacce4fd990d40218aa0676725b0e97ca932720cc1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}