Soumitro Chakrabarty

Professur für wahrnehmungsbasierte räumliche Audiosignalverarbeitung (AudioLabs) (Stiftungsprofessur) International Audio Laboratories Erlangen (AudioLabs)

AN EMPIRICAL STUDY OF VISUAL FEATURES FOR DNN BASED AUDIO-VISUAL SPEECH ENHANCEMENT IN MULTI-TALKER ENVIRONMENTS (2021) Shetu S, Chakrabarty S, Habets E Conference contribution Signal-Aware Broadband DOA Estimation Using Attention Mechanisms (2020) Mack W, Bharadwaj U, Chakrabarty S, Habets E Conference contribution Multi-scale aggregation of phase information for complexity reduction of CNN based DOA estimation (2019) Chakrabarty S, Habets E Conference contribution Time-Frequency Masking Based Online Multi-Channel Speech Enhancement with Convolutional Recurrent Neural Networks (2019) Chakrabarty S, Habets E Journal article CountNet: Estimating the number of concurrent speakers using supervised learning (2019) Stöter FR, Chakrabarty S, Edler B, Habets E Journal article Multi-speaker DOA estimation using deep convolutional networks trained with noise signals (2019) Chakrabarty S, Habets E Journal article Classification vs. regression in supervised learning for speaker count estimation (2018) Stöter FR, Chakrabarty S, Edler B, Habets E Conference contribution Time-frequency masking based online speech enhancement with multi-channel data using convolutional neural networks (2018) Chakrabarty S, Wang D, Habets E Conference contribution A Bayesian Approach to Informed Spatial Filtering with Robustness Against DOA Estimation Errors (2018) Chakrabarty S, Habets E Journal article, Original article Classification vs. regression in supervised learning for single channel speaker count estimation (2018) Stöter FR, Chakrabarty S, Edler B, Habets E Conference contribution