BUT Opensat 2019 Speech Recognition System

Keywords

Computer science, Speech recognition, Domain (mathematical analysis), Process (computing), Noise (video)

References

• Attention-Based Models for Speech RecognitionJan Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk — 2015
• The Kaldi Speech Recognition ToolkitDaniel Povey — 2011
• The language-independent bottleneck featuresKarel Veselý, Martin Karafiát, František Grézl — 2012
• Multilingual training of deep neural networksArnab Ghoshal, Paweł Świętojański, Steve Renals — 2013
• A pitch extraction algorithm tuned for automatic speech recognitionPegah Ghahremani, Bagher BabaAli, Daniel Povey — 2014
• Sequence-discriminative training of deep neural networksKarel Veselý, Arnab Ghoshal, Lukáš Burget — 2013
• Reverberation robust acoustic modeling using i-vectors with time delay neural networksVijayaditya Peddinti, Guoguo Chen, Daniel Povey — 2015
• Enhancing low resource keyword spotting with automatically retrieved web documentsLe Zhang, Damianos Karakos, William M. Hartmann — 2015
• Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMIDaniel Povey, Vijayaditya Peddinti, Daniel Gálvez — 2016
• Adapting multilingual neural network hierarchy to a new languageFrantišek Grézl, Martin Karafiát — 2014
• Hybrid CTC/Attention Architecture for End-to-End Speech RecognitionShinji Watanabe, Takaaki Hori, Suyoun Kim — 2017
• Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural NetworksDaniel Povey, Gaofeng Cheng, Yiming Wang — 2018
• BUT OpenSAT 2017 Speech Recognition SystemMartin Karafiát, Murali Karthick Baskar, Igor Szöke — 2018
• Optimizing Multilingual Knowledge Transfer for Time-Delay Neural Networks with Low-Rank FactorizationFrancis Keith, William M. Hartmann, Man-Hung Siu — 2018
• Convolutional Self-Attention NetworksBaosong Yang, Longyue Wang, Derek F. Wong — 2019
• ESPnet: End-to-End Speech Processing ToolkitShinji Watanabe, Takaaki Hori, Shigeki Karita — 2018
• 2016 BUT Babel System: Multilingual BLSTM Acoustic Model with i-Vector Based AdaptationMartin Karafiát, Murali Karthick Baskar, Pavel Matějka — 2017
• Attention is All you NeedAshish Vaswani, Noam Shazeer, Niki Parmar — 2017
• Babel system : Multilingual BLSTM acoustic model with i-vector based adaptationM. Karafiát, Murali Karthick Baskar, P. Matejka — 2017

Cited by

• Speech Activity Detection Based on Multilingual Speech Recognition SystemSeyyed Saeed Sarfjoo, Srikanth Madikeri, Petr Motlíček — 2020
• Text Augmentation for Language Models in High Error Recognition ScenarioKarel Beneš, Lukáš Burget — 2020
• A dual mode authentication technique of finger vein patterns extraction using synchronized speech signalsG. Sujani, G. M. S. Reddy — 2021
• Multitask Adaptation with Lattice-Free MMI for Multi-Genre Speech Recognition of Low Resource LanguagesSrikanth Madikeri, Petr Motlíček, Hervé Bourlard — 2021

Related papers

• Automatic Speech Recognition: Architecture, Methodologies and Challenges - A ReviewS. Karpagavalli, P. Deepika, Dr.E. Chandra — 2011
• Improving Low Resource Turkish Speech Recognition with Data Augmentation and TTSRamazan Gökay, Hülya Yalçın — 2019
• A Comprehensive View of Automatic Speech Recognition System - A Systematic Literature ReviewYogesh Kumar, Navdeep Singh — 2019
• Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech RecognitionKohei Matsuura, Masato Mimura, Shinsuke Sakai — 2020
• Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource LanguagesMatthew Wiesner, Chunxi Liu, Lucas Ondel — 2018