MAC: A unified framework boosting low resource automatic speech recognition

no code implementations • 5 Feb 2023 • Zeping Min, Qian Ge, Zhong Li, Weinan E

Furthermore, in the ASR task, MAC beats wav2vec2 (with fine-tuning) on common voice datasets of Cantonese and gets really competitive results on common voice datasets of Taiwanese and Japanese.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Why the pseudo label based semi-supervised learning algorithm is effective?

no code implementations • 18 Nov 2022 • Zeping Min, Qian Ge, Cheng Tai

The core idea of the pseudo label based semi-supervised learning algorithm is to use the model trained on the labeled data to generate pseudo labels on the unlabeled data, and then train a model to fit the previously generated pseudo labels.

Pseudo Label

SAN: a robust end-to-end ASR model architecture

no code implementations • 27 Oct 2022 • Zeping Min, Qian Ge, Guanhua Huang

In this paper, we propose a novel Siamese Adversarial Network (SAN) architecture for automatic speech recognition, which aims at solving the difficulty of fuzzy audio recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Robust Trajectory-based Density Estimation for Geometric Structure Recovery: Theory and Applications

no code implementations • 1 Oct 2022 • Turner Richmond, Namita Lokare, Qian Ge, Edgar Lobaton

We evaluate our method's effectiveness at extracting the underlying geometry and representative subsample points.

Activity Recognition Density Estimation +2