Aswin Subramanian on Aswin Subramanian https://sas91.github.io/ Recent content in Aswin Subramanian on Aswin Subramanian Hugo -- gohugo.io en-us © 2018 Sun, 15 Oct 2017 00:00:00 -0700 Deep Learning based Multi-Source Localization with Source Splitting and its Effectiveness in Multi-Talker Speech Recognition https://sas91.github.io/publication/lft/ Thu, 10 Feb 2022 00:00:00 +0000 https://sas91.github.io/publication/lft/ A Synergistic Combination of Signal Processing and Deep Learning for Robust Speech Recognition https://sas91.github.io/publication/phd-thesis/ Mon, 24 Jan 2022 00:00:00 +0000 https://sas91.github.io/publication/phd-thesis/ An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition https://sas91.github.io/publication/asru-2021/ Sat, 09 Oct 2021 00:00:00 +0000 https://sas91.github.io/publication/asru-2021/ Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localization https://sas91.github.io/publication/dasr/ Sun, 06 Jun 2021 00:00:00 +0000 https://sas91.github.io/publication/dasr/ The 2020 ESPnet Update: New Features, Broadened Applications, Performance Improvements, and Future Plans https://sas91.github.io/publication/espnet-2020-update/ Mon, 15 Feb 2021 00:00:00 +0000 https://sas91.github.io/publication/espnet-2020-update/ ESPnet-SE: End-to-End Speech Enhancement and Separation Toolkit Designed for ASR Integration https://sas91.github.io/publication/espnet-se/ Tue, 19 Jan 2021 00:00:00 +0000 https://sas91.github.io/publication/espnet-se/ End-to-End ASR with Adaptive Span Self-Attention https://sas91.github.io/publication/yj-is20/ Sun, 25 Oct 2020 00:00:00 +0000 https://sas91.github.io/publication/yj-is20/ End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming https://sas91.github.io/publication/e2e-sjtu-is20/ Sun, 25 Oct 2020 00:00:00 +0000 https://sas91.github.io/publication/e2e-sjtu-is20/ Significance of Spectral Cues in Automatic Speech Segmentation for Indian Language Speech Synthesizers https://sas91.github.io/publication/hybrid_specom/ Thu, 01 Oct 2020 00:00:00 +0000 https://sas91.github.io/publication/hybrid_specom/ CHiME-6 Challenge: Tackling Multispeaker Speech Recognition for Unsegmented Recordings https://sas91.github.io/publication/chime6-arxiv/ Mon, 04 May 2020 00:00:00 +0000 https://sas91.github.io/publication/chime6-arxiv/ The JHU Multi-Microphone Multi-Speaker ASR System for the CHiME-6 Challenge https://sas91.github.io/publication/chime6-jhu/ Mon, 04 May 2020 00:00:00 +0000 https://sas91.github.io/publication/chime6-jhu/ Attention-based ASR with Lightweight and Dynamic Convolutions https://sas91.github.io/publication/lt_d_conv-yj/ Fri, 24 Jan 2020 00:00:00 +0000 https://sas91.github.io/publication/lt_d_conv-yj/ Far-Field Location Guided Target Speech Extraction using End-to-End Speech Recognition Objectives https://sas91.github.io/publication/e2e-lgasr/ Fri, 24 Jan 2020 00:00:00 +0000 https://sas91.github.io/publication/e2e-lgasr/ Generalized Weighted-Prediction-Error Dereverberation with Varying Source Priors for Reverberant Speech Recognition https://sas91.github.io/publication/yj-waspaa19/ Sun, 20 Oct 2019 00:00:00 +0000 https://sas91.github.io/publication/yj-waspaa19/ Speech Enhancement Using End-to-End Speech Recognition Objectives https://sas91.github.io/publication/e2e-waspaa19/ Sun, 20 Oct 2019 00:00:00 +0000 https://sas91.github.io/publication/e2e-waspaa19/