paper-with-me

홈 › Papers

CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition

2019-05-27 · Linhao Dong, Bo Xu

In this paper, we propose a novel soft and monotonic alignment mechanism used for sequence transduction. It is inspired by the integrate-and-fire model in spiking neural networks and employed in the encoder-decoder framework consists of continuous functions, thus being named as: Continuous Integrate-and-Fire (CIF). Applied to the ASR task, CIF not only shows a concise calculation, but also supports online recognition and acoustic boundary positioning, thus suitable for various ASR scenarios. Several support strategies are also proposed to alleviate the unique problems of CIF-based model. With the joint action of these methods, the CIF-based model shows competitive performance. Notably, it achieves a word error rate (WER) of 2.86% on the test-clean of Librispeech and creates new state-of-the-art result on Mandarin telephone ASR benchmark.

📄 PDF Abstract BibTeX arXiv:1905.11235

Code (2)

George0828Zhang/simulst pytorch
Vladimetr/ASR-Knowledge-Transferring pytorch

Tasks

DecoderLanguage ModellingMulti-Task Learningspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Training

2023-05-27 · Linhao Dong, Zhecheng An, Peihao Wu, Jun Zhang 외

Speech or text representation generated by pre-trained models contains modal-specific information that could be combined for benefiting spoken language understanding (SLU) tasks. In this work, we propose a novel pre-trai…

intent-classificationIntent ClassificationIntent Classification and Slot FillingLanguage Modeling+5

MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognition

2025-06-04 · Yinfeng Xia, Huiyan Li, Chenyang Le, Manhong Wang 외

Applying large pre-trained speech models like Whisper has shown promise in reducing training costs for various speech tasks. However, integrating these models into streaming systems remains a challenge. This paper presen…

speech-recognitionSpeech Recognition

VILAS: Exploring the Effects of Vision and Language Context in Automatic Speech Recognition

2023-05-31 · Ziyi Ni, Minglun Han, Feilong Chen, Linghui Meng 외

Enhancing automatic speech recognition (ASR) performance by leveraging additional multimodal information has shown promising results in previous studies. However, most of these works have primarily focused on utilizing v…

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

A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition

2020-05-20 · Linhao Dong, Cheng Yi, Jianzong Wang, Shiyu Zhou 외

End-to-end models are gaining wider attention in the field of automatic speech recognition (ASR). One of their advantages is the simplicity of building that directly recognizes the speech frame sequence into the text lab…

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

Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation

2022-03-22 · Chih-Chiang Chang, Hung-Yi Lee

Simultaneous speech translation (SimulST) is a challenging task aiming to translate streaming speech before the complete input is observed. A SimulST system generally includes two components: the pre-decision that aggreg…

Translation