Caixia Gong — accepted AI-conference papers

2025

Reducing the Gap Between Pretrained Speech Enhancement and Recognition Models Using a Real Speech-Trained Bridging Module

Zhongjian Cui, Chenrui Cui, Tianrui Wang, Mengnan He, Hao Shi, Meng Ge +3

ICASSP 2025accepted

The information loss or distortion caused by single-channel speech enhancement (SE) harms the performance of automatic speech recognition (ASR). Observation addition (OA) is an effective post-processing method to improve ASR performance by balancing noisy and enhanced speech. Determining the OA coef…

Cited by 0 Source ↗Scholar ↗

2016

Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin

Dario Amodei, Sundaram Ananthanarayanan, Rishita Anubhai, Jingliang Bai, Eric Battenberg, Carl Case +63

ICML 2016poster

We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech–two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of s…

Cited by 4031 Source ↗PDF ↗code ↗Scholar ↗