Publication

Scaling up online speech recognition using ConvNets

arXiv


Abstract

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). The system has almost three times the throughput of a well tuned hybrid ASR baseline while also having lower latency and a better word error rate. We improve the core TDS architecture in order to limit the future context and hence reduce latency while maintaining accuracy. Also important to the efficiency of the recognizer is our highly optimized beam search decoder. To show the impact of our design choices, we analyze throughput, latency and accuracy and also discuss how these metrics can be tuned based on the user requirements.

Related Publications

All Publications

The Springer Series on Challenges in Machine Learning - December 12, 2019

The Second Conversational Intelligence Challenge (ConvAI2)

Emily Dinan, Varvara Logacheva, Valentin Malykh, Alexander Miller, Kurt Shuster, Jack Urbanek, Douwe Kiela, Arthur Szlam, Iulian Serban, Ryan Lowe, Shrimai Prabhumoye, Alan W. Black, Alexander Rudnicky, Jason Williams, Joelle Pineau, Jason Weston

EMNLP - November 15, 2020

Intrinsic Probing through Dimension Selection

Lucas Torroba Hennigen, Adina Williams, Ryan Cotterell

EMNLP - November 16, 2020

Pareto Probing: Trading Off Accuracy for Complexity

Tiago Pimentel, Naomi Saphra, Adina Williams, Ryan Cotterell

ICLR - May 2, 2021

What they do when in doubt: a study of inductive biases in seq2seq learners

Eugene Kharitonov, Rahma Chaabouni

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy