Gabor Simko — accepted AI-conference papers

2019

Joint Endpointing and Decoding with End-to-end Models

Shuo-Yiin Chang, Rohit Prabhavalkar, Yanzhang He, Tara N. Sainath, Gabor Simko

ICASSP 2019accepted

The tradeoff between word error rate (WER) and latency is very important for streaming automatic speech recognition (ASR) applications. We want the system to endpoint and close the microphone as quickly as possible, without degrading WER. Conventional ASR systems rely on a separately trained endpoin…

Cited by 0 Source ↗Scholar ↗

2018

Temporal Modeling Using Dilated Convolution and Gating for Voice-Activity-Detection

Shuo-Yiin Chang, Bo Li, Gabor Simko, Tara N. Sainath, Anshuman Tripathi, Aäron van den Oord +1

ICASSP 2018accepted

Voice activity detection (VAD) is the task of predicting which parts of an utterance contains speech versus background noise. It is an important first step to determine which samples to send to the decoder and when to close the microphone. The long short-term memory neural network (LSTM) is a popula…

Cited by 0 Source ↗Scholar ↗