检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Raissi, Tina Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology Group RWTH Aachen University Germany AppTek GmbH Germany

ISBN: (纸本)9798350368741

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, incorporating the right label context into the training criterion's gradient causes normalization problems and is not mathematically well-defined. The classic hybrid neural network hidden Markov model (NN-HMM) with its inherent generative formulation enables conditioning on the right label context. However, due to the HMM state-tying the identity of the right label context is never modeled explicitly. In this work, we propose a factored loss with auxiliary left and right label contexts that sums over all alignments. We show that the inclusion of the right label context is particularly beneficial when training data resources are limited. Moreover, we also show that it is possible to build a factored hybrid HMM system by relying exclusively on the full-sum criterion. Experiments were conducted on Switchboard 300h and LibriSpeech 960h. © 2025 IEEE.

关键词： CTC end-to-end factored hybrid HMM full-sum HMM

来源：评论

学校读者我要写书评

暂无评论

Right Label Context in End-to-End Training of Time-Synchronous ASR Models

Right Label Context in End-to-End Training of Time-Synchrono...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tina Raissi Ralf Schlüter Hermann Ney Machine Learning and Human Language Technology Group RWTH Aachen University AppTek GmbH Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

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, incorporating the right label context into the training criterion’s gradient causes normalization problems and is not mathematically well-defined. The classic hybrid neural network hidden Markov model (NN-HMM) with its inherent generative formulation enables conditioning on the right label context. However, due to the HMM state-tying the identity of the right label context is never modeled explicitly. In this work, we propose a factored loss with auxiliary left and right label contexts that sums over all alignments. We show that the inclusion of the right label context is particularly beneficial when training data resources are limited. Moreover, we also show that it is possible to build a factored hybrid HMM system by relying exclusively on the full-sum criterion. Experiments were conducted on Switchboard 300h and LibriSpeech 960h.

关键词： Training Hidden Markov models Training data Switches Signal processing Mathematical models Data models Speech processing Standards Context modeling

来源：评论

学校读者我要写书评

暂无评论

Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression

arXiv

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 fit hardware constraints without redundant training. Moreover, we introduce a novel method called OrthoSoftmax, which applies multiple orthogonal softmax functions to efficiently identify optimal subnets within the supernet, avoiding resource-intensive search. This approach also enables more flexible and precise subnet selection by allowing selection based on various criteria and levels of granularity. Our results with CTC on Librispeech and TED-LIUM-v2 show that FLOPs-aware component-wise selection achieves the best overall performance. With the same number of training updates from one single job, WERs for all model sizes are comparable to or slightly better than those of individually trained models. Furthermore, we analyze patterns in the selected components and reveal interesting insights. Copyright © 2025, The Authors. All rights reserved.

关键词： Orthogonal functions

来源：评论

学校读者我要写书评

暂无评论

Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression

Efficient Supernet Training with Orthogonal Softmax for Scal...

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

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

关键词： Training Speech recognition Signal processing Hardware Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Right Label Context in End-to-End Training of Time-Synchronous ASR Models

arXiv

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, incorporating the right label context into the training criterion’s gradient causes normalization problems and is not mathematically well-defined. The classic hybrid neural network hidden Markov model (NN-HMM) with its inherent generative formulation enables conditioning on the right label context. However, due to the HMM state-tying the identity of the right label context is never modeled explicitly. In this work, we propose a factored loss with auxiliary left and right label contexts that sums over all alignments. We show that the inclusion of the right label context is particularly beneficial when training data resources are limited. Moreover, we also show that it is possible to build a factored hybrid HMM system by relying exclusively on the full-sum criterion. Experiments were conducted on Switchboard 300h and LibriSpeech 960h. © 2025, CC BY.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Classification Error Bound for Low Bayes Error Conditions in machine learning

arXiv

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 replaced with a model distribution estimated from the training data in the Bayes decision rule. This substitution introduces a mismatch between the Bayes error and the model-based classification error. In this work, we apply classification error bounds to study the relationship between the error mismatch and the Kullback-Leibler divergence in machine learning. Motivated by recent observations of low model-based classification errors in many machine learning tasks, bounding the Bayes error to be lower, we propose a linear approximation of the classification error bound for low Bayes error conditions. Then, the bound for class priors are discussed. Moreover, we extend the classification error bound for sequences. Using automatic speech recognition as a representative example of machine learning applications, this work analytically discusses the correlations among different performance measures with extended bounds, including cross-entropy loss, language model perplexity, and word error rate. Copyright © 2025, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Classification Error Bound for Low Bayes Error Conditions in machine learning

Classification Error Bound for Low Bayes Error Conditions in...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zijian Yang Vahe Eminyan Ralf Schlüter Hermann Ney Computer Science Department Machine Learning and Human Language Technology Group Lehrstuhl Informatik 6 RWTH Aachen University Germany AppTek GmbH Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

关键词： Error analysis Measurement uncertainty Linear approximation Training data machine learning Signal processing Loss measurement Data models Bayes methods Speech processing

来源：评论

学校读者我要写书评

暂无评论

Leveraging Cross-Lingual Transfer learning in Spoken Named Entity Recognition Systems 20

Leveraging Cross-Lingual Transfer Learning in Spoken Named E...

引用

20th Conference on Natural language Processing, KONVENS 2024

作者： Benaicha, Moncef Thulke, David Tuğtekin Turan, M.A. Germany Machine Learning and Human Language Technology RWTH Aachen University Germany

Recent Named Entity Recognition (NER) advancements have significantly enhanced text classification capabilities. This paper focuses on spoken NER, aimed explicitly at spoken document retrieval, an area not widely studied due to the lack of comprehensive datasets for spoken contexts. Additionally, the potential for cross-lingual transfer learning in low-resource situations deserves further investigation. In our study, we applied transfer learning techniques across Dutch, English, and German using both pipeline and End-to-End (E2E) approaches. We employed Wav2Vec2 XLS-R models on custom pseudo-annotated datasets to evaluate the adaptability of cross-lingual systems. Our exploration of different architectural configurations assessed the robustness of these systems in spoken NER. Results showed that the E2E model was superior to the pipeline model, particularly with limited annotation resources. Furthermore, transfer learning from German to Dutch improved performance by 7% over the standalone Dutch E2E system and 4% over the Dutch pipeline model. Our findings highlight the effectiveness of cross-lingual transfer in spoken NER and emphasize the need for additional data collection to improve these systems. ©2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of the wav2vec 2.0 Feature Extractor 15

Comparative Analysis of the wav2vec 2.0 Feature Extractor

引用

15th ITG Conference on Speech Communication

作者： Vieting, Peter Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology RWTH Aachen University Germany AppTek GmbH Germany

ISBN: (纸本)9783800761654

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, neural raw waveform feature extractors (FEs) are an appealing approach. Also the wav2vec 2.0 model, which has recently gained large popularity, uses a convolutional FE which operates directly on the speech waveform. However, it is not yet studied extensively in the literature. In this work, we study its capability to replace the standard feature extraction methods in a connectionist temporal classification (CTC) ASR model and compare it to an alternative neural FE. We show that both are competitive with traditional FEs on the LibriSpeech benchmark and analyze the effect of the individual components. Furthermore, we analyze the learned filters and show that the most important information for the ASR system is obtained by a set of bandpass filters. © VDE VERLAG GMBH Berlin Offenbach.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization 2

Prompting and Fine-Tuning of Small LLMs for Length-Controlla...

引用

2nd International Conference on Foundation and Large language Models, FLLM 2024

作者： Thulke, David Gao, Yingbo Jalota, Rricha Dugast, Christian Ney, Hermann AppTek GmbH Aachen Germany RWTH Aachen University Machine Learning and Human Language Technology Group Germany

ISBN: (纸本)9798350354799

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 of telephone conversations, followed by the creation of a tailored synthetic training dataset utilizing stronger frontier models. We place special focus on the diversity of the generated data and on the ability to control the length of the generated summaries to meet various use-case specific requirements. The effectiveness of our method is evaluated using two state-of-the-art LLM-as-a-judge-based evaluation techniques to ensure the quality and relevance of the summaries. Our results show that fine-tuned Llama-2-7B-based summarization model performs on-par with GPT-4 in terms of factual accuracy, completeness and conciseness. Our findings demonstrate the potential for quickly bootstrapping a practical and efficient call summarization system. © 2024 IEEE.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：