Search Results for author: Songjun Cao

Found 8 papers, 1 papers with code

DistillW2V2: A Small and Streaming Wav2vec 2.0 Based ASR Model

no code implementations16 Mar 2023 Yanzhe Fu, Yueteng Kang, Songjun Cao, Long Ma

In this work, we propose a two-stage knowledge distillation method to solve these two problems: the first step is to make the big and non-streaming teacher model smaller, and the second step is to make it streaming.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Improving CTC-based speech recognition via knowledge transferring from pre-trained language models

1 code implementation22 Feb 2022 Keqi Deng, Songjun Cao, Yike Zhang, Long Ma, Gaofeng Cheng, Ji Xu, Pengyuan Zhang

Recently, end-to-end automatic speech recognition models based on connectionist temporal classification (CTC) have achieved impressive results, especially when fine-tuned from wav2vec2. 0 models.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learning

no code implementations15 Sep 2021 Keqi Deng, Songjun Cao, Long Ma

For the former task, a standard deviation constraint loss (SDC-loss) based end-to-end (E2E) architecture is proposed to identify accents under the same language.

Accented Speech Recognition Automatic Speech Recognition +3

Improving Speech Recognition Accuracy of Local POI Using Geographical Models

no code implementations7 Jul 2021 Songjun Cao, Yike Zhang, Xiaobing Feng, Long Ma

Secondly, a group of geo-specific language models (Geo-LMs) are integrated into our speech recognition system to improve recognition accuracy of long tail and homophone POI.

speech-recognition Speech Recognition

Multi-head Monotonic Chunkwise Attention For Online Speech Recognition

no code implementations1 May 2020 Baiji Liu, Songjun Cao, Sining Sun, Weibin Zhang, Long Ma

Experiments on AISHELL-1 data show that the proposed model, along with the training strategies, improve the character error rate (CER) of MoChA from 8. 96% to 7. 68% on test set.

speech-recognition Speech Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.