User profiles for V. Panchapagesan

Venkatesh Panchapagesan

Indian Institute of Management, Bangalore (INDIA)
Verified email at iimb.ernet.in
Cited by 1638

Geography and acquirer returns

VB Uysal, S Kedia, V Panchapagesan - Journal of Financial Intermediation, 2008 - Elsevier
We examine the impact of geographical proximity on the acquisition decisions of US public
firms over the period 1990–2003. Transactions where the acquirer and target firms are …

Price discovery in auction markets: A look inside the black box

A Madhavan, V Panchapagesan - The Review of Financial …, 2000 - academic.oup.com
Opening mechanisms play a crucial role in information aggregation following the overnight
nontrading period. This article examines the process of price discovery at the New York Stock …

The information content of the limit order book: evidence from NYSE specialist trading decisions

LE Harris, V Panchapagesan - Journal of Financial Markets, 2005 - Elsevier
Specialists compete with limit order traders to provide liquidity at the New York Stock
Exchange. Since specialists see all system limit orders, they enjoy a unique advantage in this …

[HTML][HTML] Multi-task learning and weighted cross-entropy for DNN-based keyword spotting

S Panchapagesan, M Sun, A Khare, S Matsoukas… - 2016 - amazon.science
We propose improved Deep Neural Network (DNN) training loss functions for more accurate
single keyword spotting on resource-constrained embedded devices. The loss function …

The changing nature of Chapter 11

ST Bharath, V Panchapagesan… - Fisher College of …, 2010 - papers.ssrn.com
The US Chapter 11 bankruptcy system has long been viewed as equity friendly, with absolute
priority deviations (APD) in favor of equity holders occurring as often as in 75% of the …

Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting

…, A Raju, G Tucker, S Panchapagesan… - 2016 IEEE spoken …, 2016 - ieeexplore.ieee.org
We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM)
networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency …

[HTML][HTML] Compressed time delay neural network for small-footprint keyword spotting

…, Y Gao, V Nagaraja, M Rodehorst, S Panchapagesan… - 2017 - amazon.science
In this paper we investigate a time delay neural network (TDNN) for a keyword spotting task
that requires low CPU, memory and latency. The TDNN is trained with transfer learning and …

[HTML][HTML] Model compression applied to small-footprint keyword spotting

G Tucker, M Wu, M Sun, S Panchapagesan, G Fu… - 2016 - amazon.science
Several consumer speech devices feature voice interfaces that perform on-device keyword
spotting to initiate user interactions. Accurate on-device keyword spotting within a tight CPU …

Monophone-based background modeling for two-stage on-device wake word detection

M Wu, S Panchapagesan, M Sun, J Gu… - … , Speech and Signal …, 2018 - ieeexplore.ieee.org
Accurate on-device wake word detection is crucial to products with far-field voice control
such as the Amazon Echo. It is quite challenging to build a wake word system with both low …

Did decimalization hurt institutional investors?

S Chakravarty, V Panchapagesan, RA Wood - Journal of Financial Markets, 2005 - Elsevier
We examine institutional trading costs around the move to penny size ticks in 2001 (ie,
decimalization). We find that overall trading costs declined, with improvements in most partitions …