Nikko Strom — accepted AI-conference papers

2021

Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems

Anish Acharya, Suranjit Adhikari, Sanchit Agarwal, Vincent Auvray, Nehal Belgamwar, Arijit Biswas +25

NAACL 2021system demonstrations

Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation. Training each component requires annotations which are hard to obtain for every new domain, limiting scalability of such sys…

Cited by 22 Source ↗PDF ↗Scholar ↗

2019

Lessons from Building Acoustic Models with a Million Hours of Speech

Sree Hari Krishnan Parthasarathi, Nikko Strom

ICASSP 2019accepted

This is a report of our lessons learned building acoustic models from 1 Million hours of unlabeled speech, while labeled speech is restricted to 7,000 hours. We employ student/teacher training on unlabeled data, helping scale out target generation in comparison to confidence model based methods, whi…

Cited by 0 Source ↗Scholar ↗

2018

Time-Delayed Bottleneck Highway Networks Using a DFT Feature for Keyword Spotting

Jinxi Guo, Ken'ichi Kumatani, Ming Sun, Minhua Wu, Anirudh Raju, Nikko Strom +1

ICASSP 2018accepted

This paper presents a novel deep neural network (DNN) architecture with highway blocks (HWs) using a complex discrete Fourier transform (DFT) feature for keyword spotting. In our previous work, we showed that the feed-forward DNN with a time-delayed bottleneck layer (TDB-DNN) directly trained from t…

Cited by 0 Source ↗Scholar ↗