Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition

no code implementations • 10 Oct 2021 • Guoli Ye, Vadim Mazalov, Jinyu Li, Yifan Gong

Hybrid and end-to-end (E2E) systems have their individual advantages, with different error patterns in the speech recognition results.

speech-recognition Speech Recognition

Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability

no code implementations • 30 Jul 2020 • Jinyu Li, Rui Zhao, Zhong Meng, Yanqing Liu, Wenning Wei, Sarangarajan Parthasarathy, Vadim Mazalov, Zhenghao Wang, Lei He, Sheng Zhao, Yifan Gong

Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Speaker-Invariant Training via Adversarial Learning

no code implementations • 2 Apr 2018 • Zhong Meng, Jinyu Li, Zhuo Chen, Yong Zhao, Vadim Mazalov, Yifan Gong, Biing-Hwang, Juang

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.

General Classification Multi-Task Learning

Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition

no code implementations • 21 Nov 2017 • Zhong Meng, Zhuo Chen, Vadim Mazalov, Jinyu Li, Yifan Gong

Unsupervised domain adaptation of speech signal aims at adapting a well-trained source-domain acoustic model to the unlabeled data from target domain.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5