paper-with-me

Papers

Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference

2023-09-26 · Masao Someki, Nicholas Eng, Yosuke Higuchi, Shinji Watanabe

Attention-based encoder-decoder models with autoregressive (AR) decoding have proven to be the dominant approach for automatic speech recognition (ASR) due to their superior accuracy. However, they often suffer from slow inference. This is primarily attributed to the incremental calculation of the decoder. This work proposes a partially AR framework, which employs segment-level vectorized beam search for improving the inference speed of an ASR model based on the hybrid connectionist temporal classification (CTC) attention-based architecture. It first generates an initial hypothesis using greedy CTC decoding, identifying low-confidence tokens based on their output probabilities. We then utilize the decoder to perform segment-level vectorized beam search on these tokens, re-predicting in parallel with minimal decoder calculations. Experimental results show that our method is 12 to 13 times faster in inference on the LibriSpeech corpus over AR decoding whilst preserving high accuracy.

📄 PDF Abstract BibTeX arXiv:2309.14922

Code (0)

등록된 구현이 없습니다.

Tasks

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

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Action Duration Prediction for Segment-Level Alignment of Weakly-Labeled Videos

2020-11-20 · Reza Ghoddoosian, Saif Sayed, Vassilis Athitsos

This paper focuses on weakly-supervised action alignment, where only the ordered sequence of video-level actions is available for training. We propose a novel Duration Network, which captures a short temporal window of t…

Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity

2023-05-07 · Jinghao Xin, Jinwoo Kim, Zhi Li, Ning li

Deep Reinforcement Learning (DRL) has exhibited efficacy in resolving the Local Path Planning (LPP) problem. However, such application in the real world is immensely limited due to the deficient training efficiency and g…

Atari GamesDeep Reinforcement LearningDiversityRobot Navigation

Towards Robust Partially Supervised Multi-Structure Medical Image Segmentation on Small-Scale Data

2020-11-28 · Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang, Min Xu 외

The data-driven nature of deep learning (DL) models for semantic segmentation requires a large number of pixel-level annotations. However, large-scale and fully labeled medical datasets are often unavailable for practica…

Data AugmentationImage SegmentationMedical Image SegmentationMulti-Task Learning+3

A Prospective-Performance Network to Alleviate Myopia in Beam Search for Response Generation

2018-08-01 · COLING 2018 8 · Zongsheng Wang, Yunzhi Bai, Bowen Wu, Zhen Xu 외

Generative dialog models usually adopt beam search as the inference method to generate responses. However, small-width beam search only focuses on the limited current optima. This deficiency named as myopic bias ultimate…

DecoderDiversityMachine TranslationResponse Generation

EgoVM: Achieving Precise Ego-Localization using Lightweight Vectorized Maps

2023-07-18 · Yuzhe He, Shuang Liang, Xiaofei Rui, Chengying Cai 외

Accurate and reliable ego-localization is critical for autonomous driving. In this paper, we present EgoVM, an end-to-end localization network that achieves comparable localization accuracy to prior state-of-the-art meth…

Autonomous DrivingAutonomous VehiclesDecoderSemantic Segmentation