Pavel Golik
Publications by Year
Research Areas
Speech Recognition and Synthesis, Music and Audio Processing, Speech and Audio Processing, Natural Language Processing Techniques, Topic Modeling
Most-Cited Works
- → Cross-entropy vs. squared error training: a theoretical and experimental comparison(2013)220 cited
- → Acoustic modeling with deep neural networks using raw time signal for LVCSR(2014)183 cited
- → Convolutional neural networks for acoustic modeling of raw time signal in LVCSR(2015)102 cited
- → Multilingual representations for low resource speech recognition and keyword search(2015)83 cited
- → RASR/NN: The RWTH neural network toolkit for speech recognition(2014)53 cited
- → Data augmentation, feature combination, and multilingual neural networks to improve ASR and KWS performance for low-resource languages(2014)44 cited
- → The RWTH/UPB/FORTH System Combination for the 4th CHiME Challenge Evaluation(2016)32 cited
- → How Might We Create Better Benchmarks for Speech Recognition?(2021)24 cited
- → Speaker adaptive joint training of Gaussian mixture models and bottleneck features(2015)22 cited
- → Non-stationary feature extraction for automatic speech recognition(2011)21 cited