paper-with-me

Papers

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 aggregates the speech information and the policy that decides to read or write. While recent works had proposed various strategies to improve the pre-decision, they mainly adopt the fixed wait-k policy, leaving the adaptive policies rarely explored. This paper proposes to model the adaptive policy by adapting the Continuous Integrate-and-Fire (CIF). Compared with monotonic multihead attention (MMA), our method has the advantage of simpler computation, superior quality at low latency, and better generalization to long utterances. We conduct experiments on the MuST-C V2 dataset and show the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2204.09595

Code (1)

George0828Zhang/simulst 공식 구현 pytorch

Tasks

Translation

Similar Papers 제목 키워드 기반

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

An adaptive large neighborhood search heuristic for the multi-port continuous berth allocation problem

2023-02-05 · Bernardo Martin-Iradi, Dario Pacino, Stefan Ropke

In this paper, we study a problem that integrates the vessel scheduling problem with the berth allocation into a collaborative problem denoted as the multi-port continuous berth allocation problem (MCBAP). This problem o…

Scheduling

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 frame…

DecoderLanguage ModellingMulti-Task Learningspeech-recognition+1

Domain Wall Magnetic Tunnel Junction Reliable Integrate and Fire Neuron

2024-05-23 · Can Cui1, Sam Liu, Jaesuk Kwon, Jean Anne C. Incorvia

In spiking neural networks, neuron dynamics are described by the biologically realistic integrate-and-fire model that captures membrane potential accumulation and above-threshold firing behaviors. Among the hardware impl…

image-classificationImage Classification

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