Training Hybrid Models on Noisy Transliterated Transcripts for Code-Switched Speech Recognition. | 0 | 0.34 | 2021 |
GigaSpeech - An Evolving, Multi-Domain ASR Corpus with 10, 000 Hours of Transcribed Audio. | 4 | 0.38 | 2021 |
Multi-task self-supervised learning for Robust Speech Recognition | 1 | 0.37 | 2020 |
Induced Inflection-Set Keyword Search In Speech | 0 | 0.34 | 2020 |
Using ASR Methods for OCR. | 0 | 0.34 | 2019 |
Bottom-Up Unsupervised Word Discovery via Acoustic Units. | 0 | 0.34 | 2019 |
Zero-Shot Pronunciation Lexicons For Cross-Language Acoustic Model Transfer | 0 | 0.34 | 2019 |
Semi-Supervised Training of DNN-Based Acoustic Model for ATC Speech Recognition. | 0 | 0.34 | 2018 |
Low-Resource Contextual Topic Identification on Speech. | 0 | 0.34 | 2018 |
Automatic Speech Recognition and Topic Identification from Speech for Almost-Zero-Resource Languages. | 0 | 0.34 | 2018 |
The JHU Speech LOREHLT 2017 System: Cross-Language Transfer for Situation-Frame Detection. | 0 | 0.34 | 2018 |
The MIT Lincoln Laboratory / JHU / EPITA-LSE LRE17 System. | 0 | 0.34 | 2018 |
Improving LF-MMI Using Unconstrained Supervisions for ASR. | 0 | 0.34 | 2018 |
A Relevance Score Estimation For Spoken Term Detection Based On Rnn-Generated Pronunciation Embeddings | 1 | 0.38 | 2017 |
The Kaldi Openkws System: Improving Low Resource Keyword Search | 3 | 0.41 | 2017 |
Topic Identification For Speech Without Asr | 1 | 0.39 | 2017 |
Using of heterogeneous corpora for training of an ASR system. | 0 | 0.34 | 2017 |
New release of Mixer-6: Improved validity for phonetic study of speaker variation and identification. | 1 | 0.36 | 2016 |
A Coarse-Grained Model for Optimal Coupling of ASR and SMT Systems for Speech Translation | 0 | 0.34 | 2015 |
Combination of FST and CN search in spoken term detection. | 6 | 0.46 | 2014 |
Low-resource open vocabulary keyword search using point process models. | 4 | 0.39 | 2014 |
Improving deep neural network acoustic models using generalized maxout networks | 110 | 4.83 | 2014 |
A keyword search system using open source software | 13 | 0.65 | 2014 |
Using proxies for OOV keywords in the keyword search task | 36 | 1.42 | 2013 |
Quantifying the value of pronunciation lexicons for keyword search in lowresource languages | 16 | 1.19 | 2013 |
Captioning of Live TV Programs through Speech Recognition and Re-speaking. | 3 | 0.47 | 2012 |
Optimized Acoustic Likelihoods Computation for NVIDIA and ATI/AMD Graphics Processors | 10 | 0.72 | 2012 |
Full Covariance Gaussian Mixture Models Evaluation On Gpu | 4 | 0.46 | 2012 |
Optimization Of The Gaussian Mixture Model Evaluation On Gpu | 3 | 0.45 | 2011 |
Online TV captioning of Czech parliamentary sessions | 5 | 0.61 | 2010 |
Posterior estimates and transforms for speech recognition | 0 | 0.34 | 2010 |
Adaptation of a feedforward artificial neural network using a linear transform | 9 | 0.64 | 2010 |
Identification And Automatic Detection Of Parasitic Speech Sounds | 2 | 0.41 | 2009 |
Voice-controlled data entry in dental electronic health record. | 2 | 0.45 | 2008 |
Feature Space Transforms For Czech Sign-Language Recognition | 1 | 0.40 | 2008 |
Silence/Speech detection method based on set of decision graphs | 0 | 0.34 | 2006 |