咨询与建议

限定检索结果

文献类型

  • 285 篇 会议
  • 112 篇 期刊文献

馆藏范围

  • 397 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 270 篇 工学
    • 196 篇 计算机科学与技术...
    • 179 篇 软件工程
    • 71 篇 信息与通信工程
    • 22 篇 生物工程
    • 20 篇 机械工程
    • 17 篇 电气工程
    • 17 篇 控制科学与工程
    • 15 篇 电子科学与技术(可...
    • 12 篇 光学工程
    • 10 篇 化学工程与技术
    • 9 篇 生物医学工程(可授...
    • 3 篇 仪器科学与技术
    • 3 篇 动力工程及工程热...
    • 2 篇 材料科学与工程(可...
    • 2 篇 土木工程
  • 169 篇 理学
    • 111 篇 物理学
    • 69 篇 数学
    • 39 篇 统计学(可授理学、...
    • 26 篇 生物学
    • 20 篇 系统科学
    • 11 篇 化学
  • 38 篇 管理学
    • 27 篇 图书情报与档案管...
    • 9 篇 管理科学与工程(可...
    • 4 篇 工商管理
    • 2 篇 公共管理
  • 6 篇 法学
    • 5 篇 社会学
  • 5 篇 医学
    • 5 篇 临床医学
    • 2 篇 基础医学(可授医学...
    • 2 篇 公共卫生与预防医...
  • 2 篇 文学
    • 2 篇 外国语言文学
  • 1 篇 经济学
  • 1 篇 教育学
  • 1 篇 农学
  • 1 篇 艺术学

主题

  • 66 篇 speech recogniti...
  • 40 篇 training
  • 38 篇 hidden markov mo...
  • 29 篇 neural machine t...
  • 25 篇 machine translat...
  • 20 篇 decoding
  • 19 篇 handwriting reco...
  • 18 篇 computer aided l...
  • 16 篇 recurrent neural...
  • 15 篇 feature extracti...
  • 15 篇 transducers
  • 14 篇 vocabulary
  • 12 篇 databases
  • 12 篇 error analysis
  • 11 篇 speech
  • 10 篇 pattern recognit...
  • 10 篇 humans
  • 9 篇 training data
  • 9 篇 optimization
  • 9 篇 context

机构

  • 52 篇 human language t...
  • 40 篇 human language t...
  • 37 篇 apptek gmbh aach...
  • 32 篇 human language t...
  • 31 篇 human language t...
  • 23 篇 apptek gmbh aach...
  • 20 篇 human language t...
  • 16 篇 human language t...
  • 13 篇 human language t...
  • 12 篇 pattern recognit...
  • 10 篇 human language t...
  • 9 篇 spoken language ...
  • 9 篇 human language t...
  • 8 篇 computer science...
  • 8 篇 human language t...
  • 6 篇 pattern recognit...
  • 6 篇 human language t...
  • 6 篇 human language t...
  • 6 篇 human language t...
  • 5 篇 a2ia sa

作者

  • 210 篇 ney hermann
  • 80 篇 hermann ney
  • 61 篇 schlüter ralf
  • 22 篇 ralf schluter
  • 21 篇 ralf schlüter
  • 20 篇 casacuberta fran...
  • 19 篇 wuebker joern
  • 18 篇 zeyer albert
  • 17 篇 zhou wei
  • 16 篇 gao yingbo
  • 14 篇 kim yunsu
  • 14 篇 herold christian
  • 13 篇 mansour saab
  • 13 篇 zeineldeen moham...
  • 13 篇 patrick doetsch
  • 12 篇 peris álvaro
  • 12 篇 peter jan-thorst...
  • 12 篇 michel wilfried
  • 12 篇 peitz stephan
  • 12 篇 huck matthias

语言

  • 395 篇 英文
  • 1 篇 西班牙文
  • 1 篇 中文
检索条件"机构=Human Language Technology And Pattern Recognition Group"
397 条 记 录,以下是351-360 订阅
排序:
CONFORMER-BASED HYBRID ASR SYSTEM FOR SWITCHBOARD DATASET
arXiv
收藏 引用
arXiv 2021年
作者: Zeineldeen, Mohammad Xu, Jingjing Lüscher, Christoph Michel, Wilfried Gerstenberger, Alexander Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany
The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on different datasets. To our best knowled... 详细信息
来源: 评论
Cumulative adaptation for BLSTM acoustic models
arXiv
收藏 引用
arXiv 2019年
作者: Kitza, Markus Golik, Pavel Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany
This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neu... 详细信息
来源: 评论
The rwth asr system for ted-lium release 2: improving hybrid hmm with specaugment
arXiv
收藏 引用
arXiv 2020年
作者: Zhou, Wei Michel, Wilfried Irie, Kazuki Kitza, Markus Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany
We present a complete training pipeline to build a state-of-the-art hybrid HMM-based ASR system on the 2nd release of the TED-LIUM corpus. Data augmentation using SpecAugment is successfully applied to improve perform... 详细信息
来源: 评论
Improved training of end-to-end attention models for speech recognition
arXiv
收藏 引用
arXiv 2018年
作者: Zeyer, Albert Irie, Kazuki Schlüter, Ralf Ney, Hermann Computer Science Department Rwth Aachen University Human Language Technology and Pattern Recognition Aachen52062 Germany AppTek United States Nnaisense Switzerland
Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h a... 详细信息
来源: 评论
Robust Beam Search for Encoder-Decoder Attention Based Speech recognition without Length Bias
arXiv
收藏 引用
arXiv 2020年
作者: Zhou, Wei Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany
As one popular modeling approach for end-to-end speech recognition, attention-based encoder-decoder models are known to suffer the length bias and corresponding beam problem. Different approaches have been applied in ... 详细信息
来源: 评论
A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models
arXiv
收藏 引用
arXiv 2020年
作者: Zeineldeen, Mohammad Zeyer, Albert Zhou, Wei Ng, Thomas Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52062 Aachen Germany AppTek GmbH Aachen52062 Germany
Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units based on e.g. byte-pair encoding (BPE... 详细信息
来源: 评论
Comparing the benefit of synthetic training data for various automatic speech recognition architectures
arXiv
收藏 引用
arXiv 2021年
作者: Rossenbach, Nick Zeineldeen, Mohammad Hilmes, Benedikt Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany
Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle t... 详细信息
来源: 评论
Confidence scores for acoustic model adaptation
Confidence scores for acoustic model adaptation
收藏 引用
International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Christian Gollan Michiel Bacchiani Human Language Technology and Pattern Recognition Computer Science Department 6 RWTH Aachen University Germany Google Inc. New York NY USA
This paper focuses on confidence scores for use in acoustic model adaptation. Frame-based confidence estimates are used in linear transform (CMLLR and MLLR) and MAP adaptation. We show that adaptation approaches with ... 详细信息
来源: 评论
ROBUST KNOWLEDGE DISTILLATION FROM RNN-T MODELS WITH NOISY TRAINING LABELS USING FULL-SUM LOSS
arXiv
收藏 引用
arXiv 2023年
作者: Zeineldeen, Mohammad Audhkhasi, Kartik Baskar, Murali Karthick Ramabhadran, Bhuvana Human Language Technology and Pattern Recognition Computer Science Department Rwth Aachen University Aachen52074 Germany Google Llc New York United States
This work studies knowledge distillation (KD) and addresses its constraints for recurrent neural network transducer (RNNT) models. In hard distillation, a teacher model transcribes large amounts of unlabelled speech t... 详细信息
来源: 评论
A comparative large scale study of MLP features for mandarin ASR
A comparative large scale study of MLP features for mandarin...
收藏 引用
作者: Valente, Fabio Doss, Mathew Magimai Plahl, Christian Ravuri, Suman Wang, Wen IDIAP Research Institute CH-1920 Martigny Switzerland Human Language Technology and Pattern Recognition RWTH Aachen University Germany International Computer Science Institute 1947 Center Street Berkeley CA 94704 United States Speech Technology and Research Laboratory SRI International Menlo Park CA United States
MLP based front-ends have shown significant complementary properties to conventional spectral features. As part of the DARPA GALE program, different MLP features were developed for Mandarin ASR. In this paper, all the... 详细信息
来源: 评论