Ehsan Variani

Publications by Year

Research Areas

Speech Recognition and Synthesis, Speech and Audio Processing, Music and Audio Processing, Natural Language Processing Techniques, Topic Modeling

Most-Cited Works

• → Deep neural networks for small footprint text-dependent speaker verification(2014)1,082 cited
• → Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition(2017)239 cited
• → Acoustic Modeling for Google Home(2017)187 cited
• → A Gaussian Mixture Model layer jointly optimized with discriminative features within a Deep Neural Network architecture(2015)60 cited
• → An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling(2021)43 cited
• → Mean temporal distance: Predicting ASR error from temporal properties of speech signal(2013)41 cited
• → Complex Linear Projection (CLP): A Discriminative Approach to Joint Feature Extraction and Acoustic Modeling(2016)30 cited
• → End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow(2017)24 cited
• → Reducing the Computational Complexity of Multimicrophone Acoustic Models with Integrated Feature Extraction(2016)18 cited
• → Multi-stream recognition of noisy speech with performance monitoring(2013)17 cited