Vadim Mazalov — accepted AI-conference papers

2022

Have Best of Both Worlds: Two-Pass Hybrid and E2E Cascading Framework for Speech Recognition

Guoli Ye, Vadim Mazalov, Jinyu Li, Yifan Gong

ICASSP 2022accepted

Hybrid and end-to-end (E2E) systems have their individual advantages, with different error patterns in the speech recognition results. By jointly modeling audio and text, the E2E model performs better in matched scenarios and scales well with a large amount of paired audio-text training data. The mo…

Cited by 0 Source ↗Scholar ↗

2018

Speaker-Invariant Training Via Adversarial Learning

Zhong Meng, Jinyu Li, Zhuo Chen, Yang Zhao, Vadim Mazalov, Yifan Gong +1

ICASSP 2018accepted

We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based ASR system. We call the scheme speaker-invariant training (…

Cited by 0 Source ↗Scholar ↗