A
Anirudh Raju
Researcher at Amazon.com
Publications - 33
Citations - 572
Anirudh Raju is an academic researcher from Amazon.com. The author has contributed to research in topics: Computer science & Language model. The author has an hindex of 11, co-authored 27 publications receiving 432 citations. Previous affiliations of Anirudh Raju include University of California, Los Angeles.
Papers
More filters
Proceedings ArticleDOI
Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting
Ming Sun,Anirudh Raju,George Tucker,Sankaran Panchapagesan,Geng-Shen Fu,Arindam Mandal,Spyros Matsoukas,Nikko Strom,Shiv Naga Prasad Vitaladevuni +8 more
TL;DR: This work proposes a max-pooling based loss function for training Long Short-Term Memory networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements and results show that LSTM models trained using cross-entropy loss or max- Pooling loss outperform a cross-ENTropy loss trained baseline feed-forward Deep Neural Network (DNN).
Posted Content
On Evaluating and Comparing Conversational Agents
Anu Venkatesh,Chandra Khatri,Ashwin Ram,Fenfei Guo,Raefer Gabriel,Ashish Nagar,Rohit Prasad,Ming Cheng,Behnam Hedayatnia,Angeliki Metallinou,Rahul Goel,Shaohua Yang,Anirudh Raju +12 more
TL;DR: This paper proposes a comprehensive evaluation strategy with multiple metrics designed to reduce subjectivity by selecting metrics which correlate well with human judgement, and believes that this work is a step towards an automatic evaluation process for conversational AIs.
Posted Content
Topic-based Evaluation for Conversational Bots
TL;DR: This work proposes to evaluate dialog quality using topic-based metrics that describe the ability of a conversational bot to sustain coherent and engaging conversations on a topic, and the diversity of topics that a bot can handle.
Proceedings ArticleDOI
Improving Noise Robustness of Automatic Speech Recognition via Parallel Data and Teacher-student Learning
Ladislav Mosner,Minhua Wu,Anirudh Raju,Sree Hari Krishnan Parthasarathi,Kenichi Kumatani,Shiva Sundaram,Roland Maas,Bjorn Hoffmeister +7 more
TL;DR: This paper adopted the teacher-student learning technique using a parallel clean and noisy corpus for improving automatic speech recognition (ASR) performance under multimedia noise and applied a logits selection method which only preserves the k highest values to prevent wrong emphasis of knowledge from the teacher and to reduce bandwidth needed for transferring data.
Proceedings ArticleDOI
Time-Delayed Bottleneck Highway Networks Using a DFT Feature for Keyword Spotting
TL;DR: Experimental results show that the TDB-HW network with the complex DFT feature provides significantly lower miss rates for a range of false alarm rates over the LFBE DNN, yielding approximately 20 % relative improvement in the area under the curve (AUC) of the detection error tradeoff (DET) curves for keyword spotting.