Skip to content

Latest commit

 

History

History
118 lines (95 loc) · 4.07 KB

talks.md

File metadata and controls

118 lines (95 loc) · 4.07 KB
layout title
page
Talks

Here is a list of my talks and presentations (including presenting work by other authors in reading groups):

  • Listening to Multi-talker Conversations: Modular and End-to-end Perspectives Slides{: .btn} Video{: .btn}
    PhD Thesis Defense
    January 26, 2024

  • VoiceBox: Text-guided multi-lingual speech generation at scale Slides{: .btn}
    Speech Technologies Reading Group
    September 22, 2023

  • Listening to Multi-talker Conversations: Modular and End-to-end Perspectives Slides{: .btn}
    Invited talk at NVIDIA Speech group
    August 18, 2023

  • FLASH Attention Slides{: .btn}
    Speech Technologies Reading Group
    April 14, 2023

  • Target Speaker Methods for Speech Recognition Slides{: .btn}
    CLSP Seminar
    March 27, 2023

  • Training RNN-T models without memory bottleneck Slides{: .btn}
    Speech Technologies Reading Group
    October 14, 2022

  • GBO presentation Slides{: .btn}
    Malone 228 (May 04, 2022)

  • Overlap-aware Speaker Diarization: Methods and Ensembles
    ISCA SIG-ML Seminar (May 05, 2021): Video{: .btn} Slides{: .btn}
    CLSP Seminar (January 29, 2021): Slides{: .btn}

  • TS-ASR: Speaker Beam and Voice Filter Slides{: .btn}
    Speech Technologies Reading Group
    October 02, 2020

  • Informed Target Speaker ASR Slides{: .btn}
    JSALT 2020 Closing Presentation
    August 06, 2020

  • Target Speaker - Voice Activity Detection Paper{: .btn} Slides{: .btn}
    Speech Technologies Reading Group
    May 29, 2020

  • The JHU Multi-Microphone Multi-Speaker ASR System for the CHiME-6 Challenge Video{: .btn} Slides{: .btn}
    CHiME-6 Virtual Workshop
    May 04, 2020

  • CLSP Seminar Lightning Talk Slides{: .btn}
    CLSP Seminar
    April 03, 2020

  • Imputer: Sequence Modeling via Imputation and Dynamic Programming Paper{: .btn} Slides{: .btn}
    Speech Technologies Reading Group
    Barton 225, 3101 Wyman Park Dr, Baltimore
    March 06, 2020

  • Transformer ASR with Contextual Block Processing Paper{: .btn} Slides{: .btn}
    Speech Technologies Reading Group
    Hackerman 320, 3101 Wyman Park Dr, Baltimore
    November 04, 2019

  • Joint CTC-Attention for ASR using Multi-task Learning Paper{: .btn} Slides{: .btn}
    Information Extraction Lightning Talk
    Hackerman 320, 3101 Wyman Park Dr, Baltimore
    May 02, 2019

  • Contrastive Predictive Coding Paper{: .btn} Slides{: .btn}
    Speech Technologies Reading Group
    Barton 225, 3101 Wyman Park Dr, Baltimore
    April 29, 2019

  • Dataset Shift in NLP Paper{: .btn} Slides{: .btn}
    NLP Reading Group
    Hackerman 306, 3101 Wyman Park Dr, Baltimore
    April 17, 2019

  • Attention-based Models for ASR Paper{: .btn} Slides{: .btn}
    Speech Technologies Reading Group
    Barton 225, 3101 Wyman Park Dr, Baltimore
    March 11, 2019