首页/论文/1209.4445

arXiv 1209.44452012-09-20cs.AI

Speech Signal Filters based on Soft Computing Techniques: A Comparison

Manav Rachna College of Engg（马纳夫拉赫纳工程学院）；K L University（K L 大学）

Sachin Lakra, T. V. Prasad, G. Ramakrishna

备注：: 5 pages
发表信息：: The 2010 International Congress on Computer Applications and Computational Science (CACS 2010), 4-6 December, 2010, Singapore

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

The paper presents a comparison of various soft computing techniques used for filtering and enhancing speech signals. The three major techniques that fall under soft computing are neural networks, fuzzy systems and genetic algorithms. Other hybrid techniques such as neuro-fuzzy systems are also available. In general, soft computing techniques have been experimentally observed to give far superior performance as compared to non-soft computing techniques in terms of robustness and accuracy.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Conversion of Acoustic Signal (Speech) Into Text By Digital Filter using Natural Language Processing

National Institute of Technology, Rourkela（鲁尔凯拉国家理工学院）

One of the most crucial aspects of communication in daily life is speech recognition. Speech recognition that is based on natural language processing is one of the essential elements in the conversion of one system to another. In this paper, we created an interface that transforms speech and other auditory inputs into text using a digital filter. Contrary to the many methods for this conversion, it is also possible for linguistic faults to appear occasionally, gender recognition, speech recognition that is unsuccessful (cannot recognize voice), and gender recognition to fail. Since technical p…

2022-09-09cs.AI

一种用于实时语音增强的两阶段分层深度滤波框架

A Two-Stage Hierarchical Deep Filtering Framework for Real-Time Speech Enhancement

Xiamen UniversityChina（厦门大学）

本文提出HDF-Net，通过子带处理与解耦为时间/频率分量的两阶段深度滤波，并引入TAConv模块，在更少资源下实现更优的实时单通道语音增强性能。

2025-06-01cs.AIcs.SDeess.AS

Kullback-Leibler度量在语音识别中的应用

Application of Kullback-Leibler Metric to Speech Recognition

本文讨论了Kullback-Leibler发散度在语音信号识别中的应用，提出了实现该发散度的三种算法：相关算法、谱算法和滤波算法。讨论涵盖了语音变异性的问题的方法，并说明了与实验建模的结果语音信号。文章给出了一些关于选择合适的模型参数的建议，并与其他一些语音识别方法进行了比较。

2003-10-13cs.AI

增强语音命令的合成训练数据：从基于ASR的过滤到SSL潜在空间中的域适应

Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Space

IRIT；Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）；Toulouse INP（图卢兹国立综合理工学院）；UT3（图卢兹第三大学）

本研究针对语音命令分类，提出基于ASR的过滤方法提升合成数据质量，并利用CycleGAN在自监督潜在空间中缩小合成与真实语音差距，实验验证了性能提升。

2024-09-19cs.AIcs.LGcs.SD

Filter and evolve: progressive pseudo label refining for semi-supervised automatic speech recognition

The Hong Kong Polytechnic University（香港理工大学）；Peking University（北京大学）；KU Leuven（鲁汶大学）；Anhui University（安徽大学）；Northwestern University（西北大学）

Fine tuning self supervised pretrained models using pseudo labels can effectively improve speech recognition performance. But, low quality pseudo labels can misguide decision boundaries and degrade performance. We propose a simple yet effective strategy to filter low quality pseudo labels to alleviate this problem. Specifically, pseudo-labels are produced over the entire training set and filtered via average probability scores calculated from the model output. Subsequently, an optimal percentage of utterances with high probability scores are considered reliable training data with trustworthy l…

2022-10-28cs.AIcs.LGcs.SD

On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration

MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Le Mans University（勒芒大学）

Pseudo-label (PL) filtering forms a crucial part of Self-Training (ST) methods for unsupervised domain adaptation. Dropout-based Uncertainty-driven Self-Training (DUST) proceeds by first training a teacher model on source domain labeled data. Then, the teacher model is used to provide PLs for the unlabeled target domain data. Finally, we train a student on augmented labeled and pseudo-labeled data. The process is iterative, where the student becomes the teacher for the next DUST iteration. A crucial step that precedes the student model training in each DUST iteration is filtering out noisy PLs…

2022-11-14cs.AIcs.LGeess.AS

更多相关论文收起更多论文

Low-Level Physiological Implications of End-to-End Learning of Speech Recognition

Idiap Research Institute（伊迪亚普研究所）

Current speech recognition architectures perform very well from the point of view of machine learning, hence user interaction. This suggests that they are emulating the human biological system well. We investigate whether the inference can be inverted to provide insights into that biological system; in particular the hearing mechanism. Using SincNet, we confirm that end-to-end systems do learn well known filterbank structures. However, we also show that wider band-width filters are important in the learned structure. Whilst some benefits can be gained by initialising both narrow and wide-band …

2022-08-22cs.AIcs.SDeess.AS

JenGAN：基于GAN的语音合成中的堆叠移位滤波器

JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesis

Seoul National University (SNU)（首尔大学（SNU））；Supertone Inc.（Supertone公司）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））

针对GAN神经声码器生成结果中的可听伪影问题，本文提出JenGAN训练策略，通过堆叠移位低通滤波器保证移位等变性以防止混叠并减少伪影，实验表明其能持续提升声码器模型在多数指标上的性能。

2024-06-10cs.AIcs.SDeess.AS

使用可变长度软池化从语音表示中去除说话人信息

Removing Speaker Information from Speech Representation using Variable-Length Soft Pooling

Seoul National University（首尔大学）

本文提出利用神经网络预测音素边界并进行可变长度软池化，以从自监督语音表示中去除说话人信息，并通过音素ABX和说话人识别任务验证其有效性。

2024-04-01cs.AIcs.SDeess.AS

面向端到端语音翻译的模态空间软对齐

Soft Alignment of Modality Space for End-to-end Speech Translation

Northeastern University（东北大学）；Harbin Engineering University（哈尔滨工程大学）；NiuTrans Research（纽创科技研究院）

针对端到端语音翻译中模态差异阻碍跨模态跨语言迁移、硬对齐会降低文本表示质量的问题，提出基于对抗训练的软对齐方法，在保留模态质量的同时构建模态不变空间，在MuST-C数据集上表现优于硬对齐且媲美专用翻译模型。

2023-12-18cs.AIcs.CLcs.SD

EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance

Although current neural text-to-speech (TTS) models are able to generate high-quality speech, intensity controllable emotional TTS is still a challenging task. Most existing methods need external optimizations for intensity calculation, leading to suboptimal results or degraded quality. In this paper, we propose EmoDiff, a diffusion-based TTS model where emotion intensity can be manipulated by a proposed soft-label guidance technique derived from classifier guidance. Specifically, instead of being guided with a one-hot vector for the specified emotion, EmoDiff is guided with a soft label where…

2023-02-16cs.AIcs.HCcs.LG

使用基于单频滤波的特征对帕金森病进行语音严重程度分类

Severity Classification of Parkinson's Disease from Speech using Single Frequency Filtering-based Features

Aalto University（阿尔托大学）

提出基于SFF的SFFCC与MFCC-SFF语音特征，利用PC-GITA数据库和SVM分类，在三种说话任务中均提升PD严重程度分类性能。

2023-08-17cs.AIcs.SDeess.AS