检索结果-内蒙古大学图书馆

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

On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognition

On the Relevance of Phoneme Duration Variability of Synthesi...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Rossenbach, Nick Hilmes, Benedikt Schluter, Ralf Rwth Aachen University Machine Learning and Human Language Technology Computer Science Departement Germany AppTek GmbH Germany

ISBN: (纸本)9798350306897

Synthetic data generated by text-to-speech (TTS) systems can be used to improve automatic speech recognition (ASR) systems in low-resource or domain mismatch tasks. It has been shown that TTS-generated outputs still do not have the same qualities as real data. In this work we focus on the temporal structure of synthetic data and its relation to ASR training. By using a novel oracle setup we show how much the degradation of synthetic data quality is influenced by duration modeling in non-autoregressive (NAR) TTS. To get reference phoneme durations we use two common alignment methods, a hidden Markov Gaussian-mixture model (HMM-GMM) aligner and a neural connectionist temporal classification (CTC) aligner. Using a simple algorithm based on random walks we shift phoneme duration distributions of the TTS system closer to real durations, resulting in an improvement of an ASR system using synthetic data in a semi-supervised setting. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Fairer Preferences Elicit Improved human-Aligned Large language Model Judgments

Fairer Preferences Elicit Improved Human-Aligned Large Langu...

引用

2024 Conference on Empirical Methods in Natural language Processing, EMNLP 2024

作者： Zhou, Han Wan, Xingchen Liu, Yinhong Collier, Nigel Vulić, Ivan Korhonen, Anna Language Technology Lab University of Cambridge United Kingdom Machine Learning Research Group University of Oxford United Kingdom

ISBN: (纸本)9798891761643

Large language models (LLMs) have shown promising abilities as cost-effective and reference-free evaluators for assessing language generation quality. In particular, pairwise LLM evaluators, which compare two generated texts and determine the preferred one, have been employed in a wide range of applications. However, LLMs exhibit preference biases and worrying sensitivity to prompt designs. In this work, we first reveal that the predictive preference of LLMs can be highly brittle and skewed, even with semantically equivalent instructions. We find that fairer predictive preferences from LLMs consistently lead to judgments that are better aligned with humans. Motivated by this phenomenon, we propose an automatic Zero-shot Evaluation-oriented Prompt Optimization framework, ZEPO, which aims to produce fairer preference decisions and improve the alignment of LLM evaluators with human judgments. To this end, we propose a zero-shot learning objective based on the preference decision fairness. ZEPO demonstrates substantial performance improvements over state-of-the-art LLM evaluators, without requiring labeled data, on representative meta-evaluation benchmarks. Our findings underscore the critical correlation between preference fairness and human alignment, positioning ZEPO as an efficient prompt optimizer for bridging the gap between LLM evaluators and human judgments. © 2024 Association for Computational Linguistics.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Analyzing And Improving Neural Speaker Embeddings for ASR 15

Analyzing And Improving Neural Speaker Embeddings for ASR

引用

15th ITG Conference on Speech Communication

作者： Lüscher, Christoph Xu, Jingjing Zeineldeen, Mohammad Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

ISBN: (纸本)9783800761654

Neural speaker embeddings encode the speaker’s speech characteristics through a DNN model and are prevalent for speaker verification tasks. However, only a few inconclusive studies have investigated the usage of neural speaker embeddings for an ASR system. In this work, we present our efforts w.r.t integrating neural speaker embeddings into a Conformer-based hybrid HMM ASR system. For ASR, our improved embedding extraction pipeline in combination with the Weighted-Simple-Add integration method results in x-vector and c-vector reaching on par performance with i-vectors. We further analyze, compare and combine different speaker embeddings. We improve our already strong baseline by switching to one cycle learning schedule while reducing the training time. By further adding neural speaker embeddings, we gain additional improvements. This results in our best Conformer-based hybrid ASR system with speaker embeddings achieving 9.0% WER on Hub5’00 and Hub5’01 while only training on SWB 300h. © 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

Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speech 15

Development of Hybrid ASR Systems for Low Resource Medical D...

引用

15th ITG Conference on Speech Communication

作者： Lüscher, Christoph Zeineldeen, Mohammad Yang, Zijian Raissi, Tina Vieting, Peter Le-Duc, Khai Wang, Weiyue Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology RWTH Aachen University Aachen52072 Germany AppTek GmbH Aachen52062 Germany

ISBN: (纸本)9783800761654

language barriers present a great challenge in our increasingly connected and global world. Especially within the medical domain, e.g. hospital or emergency room, communication difficulties, and delays may lead to malpractice and non-optimal patient care. In the HYKIST project, we consider patient-physician communication, more specifically between a German-speaking physician and an Arabic-, Vietnamese-, or Ukrainian-speaking patient. Currently, a doctor can call the Triaphon service to get assistance from an interpreter in order to help facilitate communication. The HYKIST goal is to support the usually non-professional bilingual interpreter with an automatic speech translation system to improve patient care and help overcome language barriers. In this work, we present our ASR system development efforts for this conversational telephone speech translation task in the medical domain for two language pairs, data collection, various acoustic model architectures, and dialect-induced difficulties. © VDE VERLAG GMBH Berlin Offenbach.

关键词： Telephone sets

来源：评论

学校读者我要写书评

暂无评论

End-To-End Training of a Neural HMM with Label and Transition Probabilities

End-To-End Training of a Neural HMM with Label and Transitio...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

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

ISBN: (纸本)9798350306897

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 *** implement a GPU-based forward-backward algorithm that enables the simultaneous training of label and transition *** 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 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Investigating The Effect of language Models in Sequence Discriminative Training For Neural Transducers

Investigating The Effect of Language Models in Sequence Disc...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

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

ISBN: (纸本)9798350306897

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. © 2023 IEEE.

关键词： Transducers

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

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

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

ISBN: (数字)9798350354799

ISBN: (纸本)9798350354805

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.

关键词： Training Measurement Accuracy Large language models Speech recognition Oral communication Telephone sets Data models Reliability Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality

arXiv

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 in terms of their requirements and (dis)advantages is commonly addressed, a closer comparison under similar conditions is not readily available in the literature. In this work, we present a comparison focused on the label topology and training criterion. We compare two discriminative alignment models with hidden Markov model (HMM) and connectionist temporal classification topology, and two first-order label context ASR models utilizing factored HMM and strictly monotonic recurrent neural network transducer, respectively. We use different measurements for the evaluation of the alignment quality, and compare word error rate and real time factor of our best systems. Experiments are conducted on the LibriSpeech 960h and Switchboard 300h tasks. © 2024, CC BY.

关键词： Alignment

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

arXiv

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 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-judgebased 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, CC BY-SA.

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：