咨询与建议

限定检索结果

文献类型

  • 20 篇 期刊文献
  • 20 篇 会议

馆藏范围

  • 40 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 24 篇 理学
    • 23 篇 物理学
    • 8 篇 数学
    • 7 篇 统计学(可授理学、...
    • 2 篇 化学
    • 1 篇 科学技术史(分学科...
  • 23 篇 工学
    • 17 篇 计算机科学与技术...
    • 15 篇 软件工程
    • 8 篇 信息与通信工程
    • 3 篇 电气工程
    • 3 篇 电子科学与技术(可...
    • 2 篇 机械工程
    • 2 篇 化学工程与技术
    • 1 篇 控制科学与工程
    • 1 篇 生物医学工程(可授...
  • 2 篇 教育学
    • 2 篇 心理学(可授教育学...
  • 2 篇 管理学
    • 2 篇 图书情报与档案管...
  • 1 篇 哲学
    • 1 篇 哲学
  • 1 篇 历史学
    • 1 篇 世界史
  • 1 篇 艺术学
    • 1 篇 艺术学理论
    • 1 篇 音乐与舞蹈学

主题

  • 11 篇 speech recogniti...
  • 5 篇 hidden markov mo...
  • 5 篇 data models
  • 4 篇 speech processin...
  • 4 篇 training
  • 3 篇 training data
  • 3 篇 signal processin...
  • 2 篇 conferences
  • 2 篇 modeling languag...
  • 2 篇 telephone sets
  • 2 篇 bayes methods
  • 2 篇 machine learning
  • 2 篇 transducers
  • 1 篇 reliability
  • 1 篇 reproducibility
  • 1 篇 reverberation
  • 1 篇 music informatio...
  • 1 篇 factored hybrid ...
  • 1 篇 reporting practi...
  • 1 篇 reporting standa...

机构

  • 20 篇 apptek gmbh
  • 11 篇 apptek gmbh aach...
  • 11 篇 machine learning...
  • 5 篇 apptek gmbh aach...
  • 4 篇 machine learning...
  • 3 篇 machine learning...
  • 3 篇 paderborn univer...
  • 2 篇 computer science...
  • 2 篇 machine learning...
  • 2 篇 machine learning...
  • 2 篇 rwth aachen univ...
  • 2 篇 machine learning...
  • 1 篇 kenvak research ...
  • 1 篇 comparative cogn...
  • 1 篇 machine learning...
  • 1 篇 rwth aachen univ...
  • 1 篇 tauchi research ...
  • 1 篇 computer science...
  • 1 篇 school of optome...
  • 1 篇 the university o...

作者

  • 21 篇 schlüter ralf
  • 19 篇 ney hermann
  • 9 篇 ralf schlüter
  • 8 篇 raissi tina
  • 8 篇 yang zijian
  • 7 篇 hermann ney
  • 6 篇 vieting peter
  • 6 篇 lüscher christop...
  • 4 篇 berger simon
  • 4 篇 zijian yang
  • 4 篇 xu jingjing
  • 4 篇 zeineldeen moham...
  • 4 篇 zhou wei
  • 4 篇 thulke david
  • 3 篇 schluter ralf
  • 3 篇 beck eugen
  • 3 篇 le-duc khai
  • 2 篇 gao yingbo
  • 2 篇 mann daniel
  • 2 篇 haeb-umbach rein...

语言

  • 22 篇 其他
  • 18 篇 英文
检索条件"机构=Machine Learning and Human Language Technology"
40 条 记 录,以下是11-20 订阅
Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression
arXiv
收藏 引用
arXiv 2025年
作者: Xu, Jingjing Beck, Eugen Yang, Zijian Schlüter, Ralf Machine Learning and Human Language Technology Group RWTH Aachen University Germany AppTek GmbH Germany
ASR systems are deployed across diverse environments, each with specific hardware constraints. We use supernet training to jointly train multiple encoders of varying sizes, enabling dynamic model size adjustment to fi... 详细信息
来源: 评论
Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression
Efficient Supernet Training with Orthogonal Softmax for Scal...
收藏 引用
International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Jingjing Xu Eugen Beck Zijian Yang Ralf Schlüter Machine Learning and Human Language Technology Group RWTH Aachen University Germany AppTek GmbH Germany
ASR systems are deployed across diverse environments, each with specific hardware constraints. We use supernet training to jointly train multiple encoders of varying sizes, enabling dynamic model size adjustment to fi... 详细信息
来源: 评论
Right Label Context in End-to-End Training of Time-Synchronous ASR Models
arXiv
收藏 引用
arXiv 2025年
作者: Raissi, Tina Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology Group RWTH Aachen University Germany AppTek GmbH Germany
Current time-synchronous sequence-to-sequence automatic speech recognition (ASR) models are trained by using sequence level cross-entropy that sums over all alignments. Due to the discriminative formulation, incorpora... 详细信息
来源: 评论
Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization
Prompting and Fine-Tuning of Small LLMs for Length-Controlla...
收藏 引用
Foundation and Large language Models (FLLM), International Conference on
作者: David Thulke Yingbo Gao Rricha Jalota Christian Dugast Hermann Ney AppTek GmbH Aachen Machine Learning and Human Language Technology Group RWTH Aachen University
This paper explores the rapid development of a telephone call summarization system utilizing large language models (LLMs). Our approach involves initial experiments with prompting existing LLMs to generate summaries o... 详细信息
来源: 评论
Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality
arXiv
收藏 引用
arXiv 2024年
作者: Raissi, Tina Lüscher, Christoph Berger, Simon Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology Group RWTH Aachen University Germany AppTek GmbH Germany
The ongoing research scenario for automatic speech recognition (ASR) envisions a clear division between end-to-end approaches and classic modular systems. Even though a high-level comparison between the two approaches... 详细信息
来源: 评论
Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization
arXiv
收藏 引用
arXiv 2024年
作者: Thulke, David Gao, Yingbo Jalota, Rricha Dugast, Christian Ney, Hermann AppTek GmbH Aachen Germany Machine Learning and Human Language Technology Group RWTH Aachen University Germany
This paper explores the rapid development of a telephone call summarization system utilizing large language models (LLMs). Our approach involves initial experiments with prompting existing LLMs to generate summaries o... 详细信息
来源: 评论
Chunked Attention-Based Encoder-Decoder Model for Streaming Speech Recognition
Chunked Attention-Based Encoder-Decoder Model for Streaming ...
收藏 引用
International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Mohammad Zeineldeen Albert Zeyer Ralf Schlüter Hermann Ney Computer Science Department Machine Learning and Human Language Technology RWTH Aachen University Germany AppTek GmbH Germany
We study a streamable attention-based encoder-decoder model in which either the decoder, or both the encoder and decoder, operate on pre-defined, fixed-size windows called chunks. A special end-of-chunk (EOC) symbol a...
来源: 评论
Comparative Analysis of the wav2vec 2.0 Feature Extractor
arXiv
收藏 引用
arXiv 2023年
作者: Vieting, Peter Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology RWTH Aachen University Germany AppTek GmbH Germany
Automatic speech recognition (ASR) systems typically use handcrafted feature extraction pipelines. To avoid their inherent information loss and to achieve more consistent modeling from speech to transcribed text, neur... 详细信息
来源: 评论
Combining TF-GridNet And Mixture Encoder For Continuous Speech Separation For Meeting Transcription
Combining TF-GridNet And Mixture Encoder For Continuous Spee...
收藏 引用
IEEE Spoken language technology Workshop
作者: Peter Vieting Simon Berger Thilo von Neumann Christoph Boeddeker Ralf Schlüter Reinhold Haeb-Umbach Machine Learning and Human Language Technology Group RWTH Aachen University Germany AppTek GmbH Germany Paderborn University Germany
Many real-life applications of automatic speech recognition (ASR) require processing of overlapped speech. A common method involves first separating the speech into overlap-free streams on which ASR is performed. Rece... 详细信息
来源: 评论
Classification Error Bound for Low Bayes Error Conditions in machine learning
arXiv
收藏 引用
arXiv 2025年
作者: Yang, Zijian Eminyan, Vahe Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology Group Lehrstuhl Informatik 6 Computer Science Department RWTH Aachen University Germany AppTek GmbH Germany
In statistical classification and machine learning, classification error is an important performance measure, which is minimized by the Bayes decision rule. In practice, the unknown true distribution is usually replac... 详细信息
来源: 评论