paper-with-me

Papers

BART based semantic correction for Mandarin automatic speech recognition system

2021-03-26 · Yun Zhao, Xuerui Yang, Jinchao Wang, Yongyu Gao, Chao Yan, Yuanfu Zhou

Although automatic speech recognition (ASR) systems achieved significantly improvements in recent years, spoken language recognition error occurs which can be easily spotted by human beings. Various language modeling techniques have been developed on post recognition tasks like semantic correction. In this paper, we propose a Transformer based semantic correction method with pretrained BART initialization, Experiments on 10000 hours Mandarin speech dataset show that character error rate (CER) can be effectively reduced by 21.7% relatively compared to our baseline ASR system. Expert evaluation demonstrates that actual improvement of our model surpasses what CER indicates.

📄 PDF Abstract BibTeX arXiv:2104.05507

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Automatic Spelling Correction with Transformer for CTC-based End-to-End Speech Recognition

2019-03-27 · Shiliang Zhang, Ming Lei, Zhijie Yan

Connectionist Temporal Classification (CTC) based end-to-end speech recognition system usually need to incorporate an external language model by using WFST-based decoding in order to achieve promising results. This is mo…

DecoderLanguage ModelingLanguage ModellingMachine Translation+4

Towards Comprehensive Semantic Speech Embeddings for Chinese Dialects

2026-01-12 · Kalvin Chang, Yiwen Shao, Jiahong Li, Dong Yu arxiv

Despite having hundreds of millions of speakers, Chinese dialects lag behind Mandarin in speech and language technologies. Most varieties are primarily spoken, making dialect-to-Mandarin speech-LLMs (large language model…

Speech Recognition

VoiceBank-2023: A Multi-Speaker Mandarin Speech Corpus for Constructing Personalized TTS Systems for the Speech Impaired

2023-08-27 · Jia-Jyu Su, Pang-Chen Liao, Yen-Ting Lin, Wu-Hao Li 외

Services of personalized TTS systems for the Mandarin-speaking speech impaired are rarely mentioned. Taiwan started the VoiceBanking project in 2020, aiming to build a complete set of services to deliver personalized Man…

Pronunciation Modeling of Foreign Words for Mandarin ASR by Considering the Effect of Language Transfer

2022-10-07 · Lei Wang, Rong Tong

One of the challenges in automatic speech recognition is foreign words recognition. It is observed that a speaker's pronunciation of a foreign word is influenced by his native language knowledge, and such phenomenon is k…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English

2025-05-20 · Haoyang Zhang, Hexin Liu, Xiangyu Zhang, Qiquan Zhang 외

The speech tokenizer plays a crucial role in recent speech tasks, generally serving as a bridge between speech signals and language models. While low-frame-rate codecs are widely employed as speech tokenizers, the impact…

Automatic Speech Recognitionspeech-recognitionSpeech RecognitionSpeech Tokenization+2