基于神经网络的自学习非特定人语音识别研究

详细介绍一种基于神经网络的自学习非特定人语音识别方法,首次介绍一种语音识别知识的自动检验方法——LVV法,给出系统原理图和知识库的自动完善原理;介绍一种LEA判别法,实现梯度牛顿有效结合神经网络快速学习方法,并给出了实验结果。     

语音识别技术在电话语音自动拨号中的应用

给出了一种应用于电话语音自动拨号的实时语音识别方法。该系统对特定人的语音进行识别,并将识别结果映射成相应的电话号码。实验结果表明该方法具有很高的识别精度和实时的识别速度,并且只需很小的内存空间就可以实现,是一种有效的应用于电话语音自动拨号等方面的语音识别方法。     

语音识别技术在电话语音自动拨号的应用

给出了一种应用于电话语音自动拨号的实时语音识别方法。该系统对特定人的语音进行识别,并将识别结果映射成相应的电话号码。实验结果表明该方法具有很高的识别精度和实时的识别速度,并且只需很小的内存空间就可以实现,是一种有效的应用于电话语音自动拨号等方面的语音识别方法。     

特定人汉语数码语音抗噪识别方法

本文提出一种连续隐邓尔可夫模型（ＣＨＭＭ）和人工神经网络（ＡＮＮ）相结合的鲁棒性识别方法。用于噪声环境下特定人数码语音识别,该方法以ＣＨＭＭ的输出作为系统的识别矢量,利用人工神经网络的模式分类和自学习功能,从识别矢量空间中提取语音预识别矢量,再由识别结果进行识别输出。实验证明,这种基于ＣＨＭＭＡＮＮ的数码语音识别方法明显地提高了系统的噪声鲁棒性,适用于中小词表语音识别系统。     

在线语音识别技术在数据自动录入中的应用

阐述在线语音识别技术，采用Python语言设计实现一个自动成绩录入系统，包含录音、语音识别、向Excel自动成绩填写，以及语音播放功能。     

基于深度学习的智能机器人语音自动校准系统

针对智能机器人语音校准结果不精准的问题,研究基于深度学习的智能机器人语音自动校准系统。设计语音自动校准引擎A/D电路,通过模拟信号发射范围采集与控制电路原始音频信息,利用紧凑型嵌入式音频接收器接收音频信息。整理与识别音频信息内容,获取语句文本样本集。使用深度学习的正弦和余弦函数编码处理方式构建校正模型的输入部分,通过深度学习的前馈神经网络训练输入样本,完成校正模型输出部分的构建。将训练后的样本输入到校正模型中,得到校正后的文本,实现智能机器人语音自动校准。由实验结果可知,该系统两种指令下的振幅波动范围分别为9～22 dB和7～21 dB,与实际振幅波动情况一致,具有精准校准结果。     

基于语音识别的IVR系统设计

以“股票语音查询应答演示系统”的设计为实例,详细探讨基于语音识别的IVR系统搭建。基于语音的电话网络与基于计算机的数据网络有机结合,实现电话语音信息和计算机后台数据库数据信息同步传输。该系统利用语音作为电话查询的手段,集成了交互式自动应答、自动语音识别和数据库搜索功能,以合成语音作为系统返还输出方式,实现了很强的自动应答功能。     

基于TMS320C54XDSP的语音识别装置的研究与实践

运用TMS320C5416实现了语音自动识别装置。该装置利用一种新的语音信号r阶的倒谱线性回归系数等参数构成识别的特征矢量集，运用模糊矢量量化技术实现了特定人的语音识别。实验结果表明该系统具有识别精度高、识别速度快等特点．是一种语音自动识别装置的有效的硬件实现方案。     

毫米半径麦克风阵列语音分离系统

随着语音技术的发展，越来越多语音处理系统尝试应用于现实生活。然而在实际场景中，噪声干扰是一个影响语音识别等任务准确率的重要因素。为了克服噪声问题并提升性能，需设计语音分离或增强模块。文中通过结合波束成形与神经网络设计了在毫米半径麦克风阵列场景下的语音分离系统并在语音识别任务上进行了测试。实验显示文中设计的系统对语音识别准确率有一定帮助。该方法可以应用于设备空间受限的场景中以提高性能。     

民航VHF抗干扰收发信机中的语音静噪技术研究

语音静噪实现的方法很多,本文主要研究＂载波＋音频静噪法＂法,该方法结合了抗干扰算法中基于Goertzel算法的载频估计方法以及常规基带话音静噪的不同特点来实现话音静噪。利用基于Goertzel算法的载频估计静噪方法实现有无信号或话音质量的好坏的识别和处理,而结合基带话音静噪可有效将有载波而无调制的信号识别出来,该方法不需对音频信号作复杂的识别处理。通过话音静噪处理,能够实现解调输出话音自动通断,提高语音质量等级。     

Neural networks for statistical recognition of continuous speech

In recent years there has been a significant body of work, both theoretical and experimental, that has established the viability of artificial neural networks (ANN's) as a useful technology for speech recognition. It has been shown that neural networks can be used to augment speech recognizers whose underlying structure is essentially that of hidden Markov models (HMM's). In particular, we have demonstrated that fairly simple layered structures, which we lately have termed big dumb neural networks (BDNN's), can be discriminatively trained to estimate emission probabilities for an HMM. Recently simple speech recognition systems (using context-independent phone models) based on this approach have been proved on controlled tests, to be both effective in terms of accuracy (i.e., comparable or better than equivalent state-of-the-art systems) and efficient in terms of CPU and memory run-time requirements. Research is continuing on extending these results to somewhat more complex systems. In this paper, we first give a brief overview of automatic speech recognition (ASR) and statistical pattern recognition in general. We also include a very brief review of HMM's, and then describe the use of ANN's as statistical estimators. We then review the basic principles of our hybrid HMM/ANN approach and describe some experiments. We discuss some current research topics, including new theoretical developments in training ANN's to maximize the posterior probabilities of the correct models for speech utterances. We also discuss some issues of system resources required for training and recognition. Finally, we conclude with some perspectives about fundamental limitations in the current technology and some speculations about where we can go from here     

Application of wavelet analysis and artificial neural networks in solving the problem concerning shape recognition of noisy pulsed signals

The problem concerning recognition of single pulses under the action of interferences is discussed by the example of classification of neuron action potentials. Joint applications of wavelets and artificial neural networks in solving the the given problem are analyzed. The recognition method, which is based on wavelet neural networks and ensures adjustment of the synapses of a supplementary (??wavelet??) layer, has been proposed. It is demonstrated that experimental data can efficiently be analyzed via the proposed method.     

有序聚类方法及其在神经网络语音识别中的应用

本文提出了一种新的网络结构,我们称之为有序聚类网络。这种网络能够对语音信号进行特征提取,很好地解决神经网络语音识别中的时间规整问题。有序聚类网络从输入语音信号的特征矢量序列中撮出一组固定数目的特 矢量,然后将这组特征矢量馈入神经网络分类器进行识别。和其他的神经网络语音识别方法相比较,用这种网络进行前端处理,可以缩短后端神经网络分类器的训练和识别时间,简化经分类器的网络产高的识别率。根据该 们建立了     

一种基于自组织神经网络的语音识别系统

建立了一种基于自组织神经网络的语音识别系统。对语音信号进行了预处理,提取了语音信号的线性预测系数、线性预测倒谱系数和Mel倒谱特征系数,建立了基于自组织神经网络的识别判决模型。深入分析和改进了自组织神经网络的分类聚类能力,通过加强训练和设定阈值函数的方法,有效地确定了边界神经元的归属,划分出了合理的输出模式类。验证了自组织神经网络适合于处理孤立词语音识别,并具有快速性和结构简单等特征。MATLAB仿真实验表明,语音识别率达到96%。     

语音识别与理解的研究进展

本文综述了当前语音识别理解的发展趋势和最新进展。指出美国在不依说话人的大词汇表的连续语音隐马尔柯夫模型识别方面起主导地位,日本在大词汇表的连续语音神经网络识别、模拟人工智能进行语音后处理方面起主导地位,并介绍了国际上最优秀的语音识别理解系统。     

民航陆空通话语音识别BiLSTM网络模型

民航陆空通话对民航飞行安全十分重要,但因其通话模式有特殊的语法结构与发音方式,日常语音识别声学模型无法有效应用于民航陆空通话的语音处理问题。针对民航陆空通话的特殊语境,本文提出了基于双向长短时记忆网络(BiLSTM)的民航陆空通话语音识别方法。首先,提取民航陆空通话语音的FBANK特征作为输入,以时序链式连接(CTC)为目标函数,训练BiLSTM网络得到BiLSTM/CTC模型。然后,利用声学模型,语言模型与陆空通话词典实现民航陆空通话的语音识别,并结合数据增强与数据迁移对模型进行增强训练提高语音识别性能。实验结果表明本文提出的方法适用于民航陆空通话语音识别,并且数据增强模型可有效降低民航陆空通话语音识别的词错误率。      

Towards a high quality Arabic speech synthesis system based on neural networks and residual excited vocal tract model

Text-to-speech conversion has traditionally been performed either by concatenating short samples of speech or by using rule-based systems to convert a phonetic representation of speech into an acoustic representation, which is then converted into speech. This paper describes a text-to-speech synthesis system for modern standard Arabic based on artificial neural networks and residual excited LPC coder. The networks offer a storage-efficient means of synthesis without the need for explicit rule enumeration. These neural networks require large prosodically labeled continuous speech databases in their training stage. As such databases are not available for the Arabic language, we have developed one for this purpose. Thus, we discuss various stages undertaken for this development process. In addition to interpolation capabilities of neural networks, a linear interpolation of the coder parameters is performed to create smooth transitions at segment boundaries. A residual-excited all pole vocal tract model and a prosodic-information synthesizer based on neural networks are also described in this paper.     

深度学习在雷达通信目标识别中的应用框架

深度学习是当前人工神经网络领域的研究热点,广泛应用于字符识别、图像识别和语音识别等应用中。雷达通信目标识别是通信对抗的前提和关键。文中分析了模板匹配法、DS证据理论等传统通信目标识别方法的在特征提取、模型表达方面的不足,对深度学习神经网络在通信目标识别中的应用进行了初步探讨,并提出了一种基于深度学习的通信目标识别框架。该框架和思路同样适用于雷达对抗目标识别等问题,可为深度学习在雷达目标识别领域的应用提供支撑。     

Chaotic transmission strategies employing artificial neuralnetworks

Two novel chaotic coding and decoding methods based on artificial neural networks (ANNs) are reported which employ the unimodal logistic map (LM) as an example. Coding is carried out by either modulating the LM or by generating the chaotic sequence with ANNs. In simulations speech has been coded and the resulting SNR_sig for the decoded speech has been evaluated. The results demonstrate that the two proposed methods offer a SNR_sig improvement of 4 and 20 dB over the SNR_sig obtained by using the LMS for decoding