检索结果-内蒙古大学图书馆

INVESTIGATING THE EFFECT OF language MODELS IN SEQUENCE DISCRIMINATIVE TRAINING FOR NEURAL TRANSDUCERS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Zijian Zhou, Wei Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

In this work, we investigate the effect of language models (LMs) with different context lengths and label units (phoneme vs. word) used in sequence discriminative training for phoneme-based neural transducers. Both lattice-free and N-best-list approaches are examined. For lattice-free methods with phoneme-level LMs, we propose a method to approximate the context history to employ LMs with full-context dependency. This approximation can be extended to arbitrary context length and enables the usage of word-level LMs in lattice-free methods. Moreover, a systematic comparison is conducted across lattice-free and N-best-list-based methods. Experimental results on Librispeech show that using the word-level LM in training outperforms the phoneme-level LM. Besides, we find that the context size of the LM used for probability computation has a limited effect on performance. Moreover, our results reveal the pivotal importance of the hypothesis space quality in sequence discriminative training. Copyright © 2023, The Authors. All rights reserved.

关键词： Transducers

END-TO-END TRAINING OF A NEURAL HMM WITH LABEL AND TRANSITION PROBABILITIES

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Mann, Daniel Raissi, Tina Michel, Wilfried Schlüter, Ralf Ney, Hermann AppTek GmbH Aachen52062 Germany Machine Learning and Human Language Technology Computer Science Department RWTH Aachen University Aachen52074 Germany

We investigate a novel modeling approach for end-to-end neural network training using hidden Markov models (HMM) where the transition probabilities between hidden states are modeled and learned explicitly. Most contemporary sequence-to-sequence models allow for from-scratch training by summing over all possible label segmentations in a given topology. In our approach there are explicit, learnable probabilities for transitions between segments as opposed to a blank label that implicitly encodes duration statistics. We implement a GPU-based forward-backward algorithm that enables the simultaneous training of label and transition probabilities. We investigate recognition results and additionally Viterbi alignments of our models. We find that while the transition model training does not improve recognition performance, it has a positive impact on the alignment quality. The generated alignments are shown to be viable targets in state-of-the-art Viterbi trainings. © 2023, CC BY.

关键词： Hidden Markov models

Competitive and Resource Efficient Factored Hybrid HMM Systems are Simpler Than You Think

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Raissi, Tina Lüscher, Christoph Gunz, Moritz Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

Building competitive hybrid hidden Markov model (HMM) systems for automatic speech recognition (ASR) requires a complex multi-stage pipeline consisting of several training criteria. The recent sequence-to-sequence models offer the advantage of having simpler pipelines that can start from-scratch. We propose a purely neural based single-stage from-scratch pipeline for a context-dependent hybrid HMM that offers similar simplicity. We use an alignment from a full-sum trained zero-order posterior HMM with a BLSTM encoder. We show that with this alignment we can build a Conformer factored hybrid that performs even better than both a state-of-the-art classic hybrid and a factored hybrid trained with alignments taken from more complex Gaussian mixture based systems. Our finding is confirmed on Switchboard 300h and LibriSpeech 960h tasks with comparable results to other approaches in the literature, and by additionally relying on a responsible choice of available computational resources. © 2023, CC BY.

关键词： Hidden Markov models

Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Jingjing Zhou, Wei Yang, Zijian Beck, Eugen Schlüter, Ralf Machine Learning and Human Language Technology Group Computer Science Dept. RWTH Aachen University Germany AppTek GmbH Aachen52062 Germany

Varying-size models are often required to deploy ASR systems under different hardware and/or application constraints such as memory and latency. To avoid redundant training and optimization efforts for individual models of different sizes, we present the dynamic encoder size approach, which jointly trains multiple performant models within one supernet from scratch. These subnets of various sizes are layer-wise pruned from the supernet, and thus, enjoy full parameter sharing. By combining score-based pruning with supernet training, we propose two novel methods, Simple-Top-k and Iterative-Zero-Out, to automatically select the best-performing subnets in a data-driven manner, avoiding resource-intensive search efforts. Our experiments using CTC on both Librispeech and TED-LIUM-v2 corpora show that our methods can achieve on-par performance as individually trained models of each size category. Also, our approach consistently brings small performance improvements for the full-size supernet. Copyright © 2024, The Authors. All rights reserved.

关键词：

Refined Statistical Bounds for Classification Error Mismatches with Constrained Bayes Error

学校读者我要写书评

暂无评论

arXiv 2024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

关键词： Adversarial machine learning

RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Wei Beck, Eugen Berger, Simon Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

Modern public ASR tools usually provide rich support for training various sequence-to-sequence (S2S) models, but rather simple support for decoding open-vocabulary scenarios only. For closed-vocabulary scenarios, public tools supporting lexical-constrained decoding are usually only for classical ASR, or do not support all S2S models. To eliminate this restriction on research possibilities such as modeling unit choice, we present RASR2 in this work, a research-oriented generic S2S decoder implemented in C++. It offers a strong flexibility/compatibility for various S2S models, language models, label units/topologies and neural network architectures. It provides efficient decoding for both open- and closed-vocabulary scenarios based on a generalized search framework with rich support for different search modes and settings. We evaluate RASR2 with a wide range of experiments on both switchboard and Librispeech corpora. Our source code is public online. Copyright © 2023, The Authors. All rights reserved.

关键词： Speech recognition

Medical Spoken Named Entity Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Le-Duc, Khai Thulke, David Tran, Hung-Phong Vo-Dang, Long Nguyen, Khai-Nguyen Hy, Truong-Son Schlüter, Ralf Lehrstuhl Informatik 6 - Machine Learning and Human Language Technology Group Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany University of Toronto Canada University Health Network Canada FPT Software AI Center Viet Nam Indiana State University United States Hanoi University of Science and Technology Viet Nam University of Cincinnati United States College of William and Mary United States

Spoken Named Entity Recognition (NER) aims to extracting named entities from speech and categorizing them into types like person, location, organization, etc. In this work, we present VietMed-NER - the first spoken NER dataset in the medical domain. To our best knowledge, our real-world dataset is the largest spoken NER dataset in the world in terms of the number of entity types, featuring 18 distinct types. Secondly, we present baseline results using various state-of-the-art pre-trained models: encoder-only and sequence-to-sequence. We found that pre-trained multilingual models XLM-R outperformed all monolingual models on both reference text and ASR output. Also in general, encoders perform better than sequence-to-sequence models for the NER task. By simply translating, the transcript is applicable not just to Vietnamese but to other languages as well. All code, data and models are made publicly available here. © 2024, CC BY.

关键词：

Music, Computing, and Health: A Roadmap for the Current and Future Roles of Music technology for Health Care and Well-Being

学校读者我要写书评

暂无评论

Music and Science 2021年 4卷

作者： Agres, Kat R. Schaefer, Rebecca S. Volk, Anja van Hooren, Susan Holzapfel, Andre Dalla Bella, Simone Müller, Meinard de Witte, Martina Herremans, Dorien Ramirez Melendez, Rafael Neerincx, Mark Ruiz, Sebastian Meredith, David Dimitriadis, Theo Magee, Wendy L. Yong Siew Toh Conservatory of Music National University of Singapore Singapore Social and Cognitive Computing Department Institute of High Performance Computing A*STAR Singapore Institute for Psychology Health Medical Neuropsychology Unit Leiden University Leiden Netherlands Leiden Institute for Brain and Cognition Leiden University Leiden Netherlands Academy of Creative and Performing Arts Leiden University Leiden Netherlands Department of Information and Computing Sciences Utrecht University Utrecht Netherlands Faculty of Health care Department of Arts Therapies Zuyd University of Applied Sciences Heerlen Netherlands KenVaK Research Centre for the Arts Therapies and Psychomotricity Heerlen Netherlands Faculty of Psychology Open University of The Netherlands Heerlen Netherlands Division of Media Technology and Interaction Design KTH Royal Institute of Technology Stockholm Sweden International Laboratory for Brain Music and Sound Research (BRAMS) Outremont QC Canada Department of Psychology University of Montreal Montreal QC Canada Centre for Research on Brain Language and Music (CRBLM) Montreal QC Canada University of Economics and Human Sciences in Warsaw Warsaw Poland International Audio Laboratories Erlangen Friedrich-Alexander Universität Erlangen-Nürnberg Erlangen Germany HAN University of Applied Sciences Department of Arts Therapies and Psychological Studies Nijmegen Netherlands University of Amsterdam Research Institute of Child Development and Education Amsterdam Netherlands Treatment Centre for People with Mild Intellectual Disabilities and Psychiatric and Behavioral Disorders Gennep Netherlands Information Systems Technology and Design Singapore University of Technology and Design Singapore Music and Machine Learning Lab Music Technology Group Universitat Pompeu Fabra Barcelona Spain Faculty of EEMCS Interactive Intelligence Group Delft University of Technology Delft Netherlands Centre for Digital Music School of Electronic Engineerin

The fields of music, health, and technology have seen significant interactions in recent years in developing music technology for health care and well-being. In an effort to strengthen the collaboration between the involved disciplines, the workshop “Music, Computing, and Health” was held to discuss best practices and state-of-the-art at the intersection of these areas with researchers from music psychology and neuroscience, music therapy, music information retrieval, music technology, medical technology (medtech), and robotics. Following the discussions at the workshop, this article provides an overview of the different methods of the involved disciplines and their potential contributions to developing music technology for health and well-being. Furthermore, the article summarizes the state of the art in music technology that can be applied in various health scenarios and provides a perspective on challenges and opportunities for developing music technology that (1) supports person-centered care and evidence-based treatments, and (2) contributes to developing standardized, large-scale research on music-based interventions in an interdisciplinary manner. The article provides a resource for those seeking to engage in interdisciplinary research using music-based computational methods to develop technology for health care, and aims to inspire future research directions by evaluating the state of the art with respect to the challenges facing each field. © The Author(s) 2021.

关键词： health care interdisciplinarity MedTech music information retrieval (MIR) music neuroscience Music psychology music technology music therapy well-being

Eye tracking: empirical foundations for a minimal reporting guideline

学校读者我要写书评

暂无评论

Behavior research methods 2023年第1期55卷 364-416页

作者： Kenneth Holmqvist Saga Lee Örbom Ignace T C Hooge Diederick C Niehorster Robert G Alexander Richard Andersson Jeroen S Benjamins Pieter Blignaut Anne-Marie Brouwer Lewis L Chuang Kirsten A Dalrymple Denis Drieghe Matt J Dunn Ulrich Ettinger Susann Fiedler Tom Foulsham Jos N van der Geest Dan Witzner Hansen Samuel B Hutton Enkelejda Kasneci Alan Kingstone Paul C Knox Ellen M Kok Helena Lee Joy Yeonjoo Lee Jukka M Leppänen Stephen Macknik Päivi Majaranta Susana Martinez-Conde Antje Nuthmann Marcus Nyström Jacob L Orquin Jorge Otero-Millan Soon Young Park Stanislav Popelka Frank Proudlock Frank Renkewitz Austin Roorda Michael Schulte-Mecklenbeck Bonita Sharif Frederick Shic Mark Shovman Mervyn G Thomas Ward Venrooij Raimondas Zemblys Roy S Hessels Department of Psychology Nicolaus Copernicus University Torun Poland. kenneth.holmqvist@ur.de. Department of Computer Science and Informatics University of the Free State Bloemfontein South Africa. kenneth.holmqvist@ur.de. Department of Psychology Regensburg University Regensburg Germany. kenneth.holmqvist@ur.de. Department of Psychology Regensburg University Regensburg Germany. Experimental Psychology Helmholtz Institute Utrecht University Utrecht The Netherlands. Lund University Humanities Lab and Department of Psychology Lund University Lund Sweden. Department of Ophthalmology SUNY Downstate Health Sciences University Brooklyn NY USA. Tobii Pro AB Danderyd Sweden. Social Health and Organizational Psychology Utrecht University Utrecht The Netherlands. Department of Computer Science and Informatics University of the Free State Bloemfontein South Africa. TNO Soesterberg The Netherlands. Department of Ergonomics Leibniz Institute for Working Environments and Human Factors Dortmund Germany. Institute of Informatics LMU Munich Munich Germany. Institute of Child Development University of Minnesota Minneapolis USA. School of Psychology University of Southampton Southampton UK. School of Optometry and Vision Sciences Cardiff University Cardiff UK. Department of Psychology University of Bonn Bonn Germany. Vienna University of Economics and Business Vienna Austria. Department of Psychology University of Essex Essex UK. Department of Neuroscience Erasmus MC Rotterdam The Netherlands. Machine Learning Group Department of Computer Science IT University of Copenhagen Copenhagen Denmark. SR Research Ltd Ottawa Canada. Human-Computer Interaction University of Tübingen Tübingen Germany. University of British Columbia Columbia Canada. Department of Eye and Vision Science Institute of Life Course and Medical Sciences University of Liverpool Liverpool UK. Department of Education and Pedagogy Division Education Faculty of Social and Behavioral Sciences Ut

In this paper, we present a review of how the various aspects of any study using an eye tracker (such as the instrument, methodology, environment, participant, etc.) affect the quality of the recorded eye-tracking data and the obtained eye-movement and gaze measures. We take this review to represent the empirical foundation for reporting guidelines of any study involving an eye tracker. We compare this empirical foundation to five existing reporting guidelines and to a database of 207 published eye-tracking studies. We find that reporting guidelines vary substantially and do not match with actual reporting practices. We end by deriving a minimal, flexible reporting guideline based on empirical research (Section "An empirically based minimal reporting guideline").

关键词： Data quality Eye movements Eye tracking Replicability Reporting guidelines Reporting practices Reporting standards Reproducibility