Description: 这个文档对想用DSP实现一非特定人语音识别系统 有很大的帮助。-this document right to use a DSP-independent speech recognition system is a great help. Platform: |
Size: 1095828 |
Author:刘品 |
Hits:
Description: 这个文档对想用DSP实现一非特定人语音识别系统 有很大的帮助。-this document right to use a DSP-independent speech recognition system is a great help. Platform: |
Size: 1095680 |
Author:刘品 |
Hits:
Description: Generalized Mel frequency cepstral coefficients for large-vocabulary Speaker-Independent Continuous-Speech Recognition 关于MFCC算法的很好的英语文章-Generalized Mel frequency cepstral coefficients for large-vocabulary Speaker-Independent Continuous-Speech Recognition on the MFCC algorithm is a very good article in English Platform: |
Size: 165888 |
Author:xiang |
Hits:
Description: speech recognition using hidden markov model making it speaker independent
Using Matlab 7.5[2008b] Platform: |
Size: 10031104 |
Author:kani |
Hits:
Description: HMM语音识别，文本相关或文本无关均使用的说话人模型-HMM speech recognition, text-related or text-independent speaker model are used Platform: |
Size: 776192 |
Author:vivilau |
Hits:
Description: The Goal of Speech Recognition (ASR) is to Accurately and efficiently convert a speech signal into a text message independent of the device, speaker or the environment.
Speech recognition technologies can be a vital step in bringing the Information Technology world to the Indian masses. Speech recognition makes use of specific AI (artificial intelligence) rules to determine what words the speaker is speaking.
Speech recognition programs have now reached over 95 accuracy, and are capable of transcribing over 160 words per minute.
-The Goal of Speech Recognition (ASR) is to Accurately and efficiently convert a speech signal into a text message independent of the device, speaker or the environment.
Speech recognition technologies can be a vital step in bringing the Information Technology world to the Indian masses. Speech recognition makes use of specific AI (artificial intelligence) rules to determine what words the speaker is speaking.
Speech recognition programs have now reached over 95 accuracy, and are capable of transcribing over 160 words per minute.
Platform: |
Size: 269312 |
Author:raj |
Hits:
Description: 说话人识别 语音识别的一部分 可以进行与文本无关的说话人识别-Speaker recognition can be a part of speech recognition and text-independent speaker recognition Platform: |
Size: 2054144 |
Author: |
Hits:
Description: 说话人识别 语音识别的一部分 可以进行与文本无关的说话人识别-Speaker recognition can be a part of speech recognition and text-independent speaker recognition Platform: |
Size: 729088 |
Author: |
Hits:
Description: 说话人识别 语音识别的一部分 可以进行与文本无关的说话人识别 此为信道补偿部分-Speaker recognition can be a part of speech recognition and text-independent speaker recognition for this part of the channel compensation Platform: |
Size: 12288 |
Author: |
Hits:
Description: 说话人识别 语音识别的一部分 可以进行与文本无关的说话人识别 此为训练语音部分-Speaker recognition can be a part of speech recognition and text-independent speaker recognition for this part of the training speech Platform: |
Size: 189440 |
Author: |
Hits:
Description: 说话人识别 语音识别的一部分 可以进行与文本无关的说话人识别 此为训练说话人模型部分-Speaker recognition can be a part of speech recognition and text-independent speaker identification speaker model in this part of the training Platform: |
Size: 15360 |
Author: |
Hits:
Description: An integrated study of speaker normalisation and HMM
adaptation for noise robust speaker-independent speech
recognition Platform: |
Size: 186368 |
Author:HOU |
Hits:
Description: 调信息在汉语语音识别中具有非常重要的意义。采用支持向量机对连续汉语连续语音进行声调识别实
验，首先采用基于Teager能量算子和过零率的两级判别策略对连续语音进行浊音段提取，然后建立了适合于支持向
量机分类模型的等维声调特征向量。使用6个二类SVM模型对非特定人汉语普通话的4种声调进行分类识别，与
BP神经网络相比，支持向量杌具有更高的识别率。-Tone is an essential component for word formation in Chinese languages．It plays a very important role in the
transmission of information in speech communication．We looked at using support vector machines(SVMs)for auto—
matic tone recognition in continuously spoken Mandarin．The voiced segments were detected based on Teager Energy
Operation and ZCIL Compared with BP neural network。considerable improvement was achieved by adopting 6 binary-
SVMs scheme in a speaker-independent Mandarin tone recognition system． Platform: |
Size: 316416 |
Author:沈 |
Hits:
Description: 语音识别芯片资料
产品介绍
应用于消费类电子产品上的交互式语音集成芯片（RSC-100/164T，RSC-300/364，RSC4XX）是一种高性能、低成本的8位MCU，所有这类芯片内部集成有ADC、DAC、ROM（除了RSC-100/300）、RAM和麦克风的预放大电路，并拥有以下多种功能：与说话者无关/有关的语音识别、语音确认（PASSWORD）、语音和音乐合成，录音和回放、快速数字拨号（只有RSC-300/364）、持续监听。
产品线有两种通用目的的微处理器（RSC系列）
-Introduction speech recognition chip data used in consumer electronics products on the interactive voice integrated chip (RSC-100/164T, RSC-300/364, RSC4XX) is a high performance, low-cost 8-bit MCU, all such An on-chip ADC, DAC, ROM (besides RSC-100/300), RAM and microphone pre-amplifier circuit, and has the following functions: speaker-independent/related speech recognition, speech recognition (PASSWORD), voice and music synthesis, recording and playback, fast-digit dialing (only RSC-300/364), continuous monitoring. Product line, there are two general-purpose microprocessor (RSC Series) Platform: |
Size: 7168 |
Author:99 |
Hits:
Description: Finally, probability analysis, based on the chosen database, is performed and
judgment whether the person is recognized is pronounced. Two different modeling
techniques can be suggested for purposes of person identification or verification. The
approach based on Hidden Markov Speaker Models (HMMs) with the mixtures of
Gaussian distribution is text-dependent one. For this technology a speaker is
described by a set of HMMs, constructing the set of speech groups spoken by that
person. The speech groups may be phonemes or words [7]. The text-independent
technology is rested upon Gaussian Mixture Speaker Models. For this technology
each speaker is defined by only one model describing all utterances of that person.
Identification in the range of both approaches is executed by evaluation of maximum
a posteriori probability [7]. Platform: |
Size: 3019776 |
Author:rasul |
Hits:
Search - speaker independent speech