Prateek Verma - Invited Talks at Academia and Industry

Sorted by Year

2022

DSP Seminar, “Transformers for Applications in Audio, Speech and Music: From Language Modeling to Understanding to Synthesis”, CCRMA, Stanford University, May 2022
EE Department Seminar, “Transformers for Audio Signal Processing”, Indian Institute of Science Bangalore, Aug 2022
Digital Audio Processing Lab, Department of Electrical Engineering, “Transformers for Applications in Audio, Speech and Music”, IIT Bombay, Powai, March 2022
Stanford Summer Workshop on Deep Learning, “Transformers For Audio”, CCRMA, Stanford University
DSP Seminar, Audio Understanding and Room Acoustics in the Era of AI, CCRMA,Stanford University, Oct 2022
The Music Engagement Research Initiative Seminar, “AI picked Room Acoustics + Generating Coherent Drums with Fills and Improvisations ”, CCRMA, Stanford University, Oct 2022
Open House, CCRMA, “Audio Understanding By Solving Jigsaw Puzzles + Room Acoustics in Era of AI”, Stanford University, 2022, Stanford, CA.
Guest Lecture, ENG 225D, “Transformers for Audio Signal Processing”, Department of EECS, University of California, Berkeley, Nov 2022, Berkeley CA

Guest Lecture, “CS 25: Transformers United”, “Transformers for Applications in Audio, Speech and Music: From Language Modeling to Understanding to Synthesis”, Department of Computer Science, Stanford University.

(Video Featured on Stanford's Universities YouTube Channel with over 4,000 views)

Invited Talk, “Self-Supervised Learning for Music and Audio”, Department of Electrical Engineering, IIT Bombay, Dec 2020
Webinar, Edgistify Inc, “Machine Learning for Businesses”, Virtual Talk, May 2020.
Invited Talk, Interactive Perception and Robotics Lab, “Audio Perception, Embeddings and Sounds of Touch”, Jan 2020, Stanford AI Lab, Jeannette Bohg Lab, Stanford University.

Invited Talk, Dolby Laboratories Inc, Learning Audio Embeddings From Signal Representation to Audio Transformations and Understanding, San Francisco, CA, June 2019
Invited Talk, Department of Electrical Engineering, Indian Institute of Technology, Bombay Learning Audio Embeddings, From Representation, Transforms, Understanding and Recommendations, Nov 2019
Salisbury Robotics Lab, AI Lab, Stanford University, Stanford, USA, Hearing Perception for Robotic Tasks, August 2019
Hearing Seminar, CCRMA, Stanford University: “Learning Audio Embeddings: From Signal Representation to Audio Transformations and Understandings”, May 2019
Guest Lecture: EE 264 Digital Signal Processing, Stanford University: Neuralogram: A Deep Neural Network Based Representation for Audio Signals, May 2019
University of Mumbai, SAKEC, Mumbai, India, Feb 2019 “Using Machine Learning For Signal Processing: Its All About Convolution”

Indian Institute of Technology, Bombay (IITB) Electrical Engineering Department Seminar Series, Supervised and Unsupervised Audio Transforms, Powai, Mumbai, April 2018
Invited Talk, Prakash Lab, Stanford Department of Bioengineering, "Pitch detection, learning T-F Masks, Supervised and Unsupervised Audio Transforms, Stanford, USA, March 2018
Hearing Seminar, CCRMA, Stanford University: “Audio Style Transfer for Deep Neural Nets”, Jan 2018

“Invited talk, Google Research, Brain Team, “Neural Style Transfer for Audio”, Nov 2017, Mountain View CA
“Stanford University CS Annual Affiliates Meeting” Arrillaga Alumni Center, Best of both Worlds: Combining Signal Processing with Deep Learning for Audio Source Separation, April 2017, Stanford CA
Guest Lecture: EE 264 Digital Signal Processing, Stanford University: Deep Learning and Signal Processing, March 2017

“EE Seminar, Department of EE, IIT Bombay”: Frequency estimation from raw waveforms”, Dec 2016
Stanford Research Institute (SRI), Menlo Park: “Pitch estimation from raw audio signals”, Dec 2016
Hearing Seminar, CCRMA, Stanford University: “Pitch estimation from raw audio signals”, Nov 2016
DSP Seminar, CCRMA, Stanford University: “Introduction to Deep Learning”, Oct 2016.
Stanford Deep Learning Reading Group: “SoundNet: Unsupervised Audio Understanding ”, Feb 2017, Stanford CA
Stanford Deep Learning Reading Group: “Speech Recognition: Deep Speech, CLDNNs and LAS architectures”, Feb 2016, Sep 2015.

Oral presentation at 40th IEEE ICASSP: “Structural Segmentation of Hindustani Concert Audios with Posterior Features”, April 2015.
DSP Seminar, CCRMA, Stanford University: “Structural Segmentation of Hindustani Concert Audios with Posterior Features”, Oct 2014
3rd CompMusic Workshop, IIT Chennai : “Melody based style detection in Hindustani Music”, Dec 2013
Acoustics 2013, Delhi: “Distinguishing Music Instrument Playing Styles with Acoustic Signal Analysis,”
25th IEEE International Conference on VLSI Design and Embedded System: “Real time melodic accompaniment system for Indian Music using TMS320C6713”, Hyderabad, 2012.