Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userطريقة النص المستقل لتحديد هوية المتحدث باستخدام صوته
734
1 11
0
(
0
)
Added by
Aِl-Baath University ورقة بحثية
Publication date
2016
fields
Informatics Engineering
and research's language is
العربية
Authors
حسان محمد أحمد( باحث )
Created by
Shamra Editor
Ask ChatGPT about the research
تم في هذا البحث دراسة طريقة النص المستقل (Text-independent) لتحديد هوية الشخص باستخدام صوته (Voice Identification) و المبنية على أساس استخراج المي ا زت/السمات (Features) الخاصة من الإشارة الصوتية، و التي تميز التنبؤ الخطي (Linear Prediction) لسلوك دالة الترابط الذاتي (Autocorrelation Function) لسبستروم (Cepstrum) الإشارة الصوتية.
In this paper, the text-independent method of person voice identification based on the features extraction from speech signal that characterize the linear prediction of the behavior of the autocorrelation function of the voice signal cepstrum are considered and developed.
References used
REYNOLDS, D, 1994 Experimental evaluation of features for robust speaker identification. IEEE Trans. On Speech and Audio Processing. Vol. 2. No. 4, 639–643
BIMBOT, F, A, 2004 tutorial on text-independent speaker verification. EURASIP J. on Applied Signal Processing. No. 4, 430–451
REYNOLDS, D; ROSE, R, 1995 Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans. On Speech and Audio Processing. No. 3, 72–83
rate research
Read More
The analysis of time series data is one of the most important statistical
topics, usually focuses on forecasting the future behavior of the series at a
certain time for certain purposes.
The current researches are moving towards more development in order to provide the
growing the needs of users such as support real-time applications, quality of service,
particularly; the high data rate transfer and other. That prompts the network
service
providers to integrate many properties for different networks resource, and support
providing the service "anywhere and anytime".
Hence, the importance of this research, which aims to study the vertical handover as
very important and necessary step to provide the mobility of mobile nodes between the
different networks by using Media Independent Handover (MIH) IEEE802.21standard
which is developed in January 2009. In this paper, the performance of vertical handover
between these two networks is evaluated taking into account many parameters such as
packet loss, handover latency, and throughput, using NS2 simulator (Network Simulator
version2) which includes a support for MIH technology by the National Institute of
Standard and Technology (NIST).
أجريت الدراسة في مخابر كلية الزراعة قسم علوم الاغذية ومخابر الميكروبيولوجيا والمناعيات بقسم البيولوجيا الجزيئية والتقانة الحيوية بهيئة الطاقة الذرية.
With the growing popularity of smart speakers, such as Amazon Alexa, speech is becoming one of the most important modes of human-computer interaction. Automatic speech recognition (ASR) is arguably the most critical component of such systems, as erro
rs in speech recognition propagate to the downstream components and drastically degrade the user experience. A simple and effective way to improve the speech recognition accuracy is to apply automatic post-processor to the recognition result. However, training a post-processor requires parallel corpora created by human annotators, which are expensive and not scalable. To alleviate this problem, we propose Back TranScription (BTS), a denoising-based method that can create such corpora without human labor. Using a raw corpus, BTS corrupts the text using Text-to-Speech (TTS) and Speech-to-Text (STT) systems. Then, a post-processing model can be trained to reconstruct the original text given the corrupted input. Quantitative and qualitative evaluations show that a post-processor trained using our approach is highly effective in fixing non-trivial speech recognition errors such as mishandling foreign words. We present the generated parallel corpus and post-processing platform to make our results publicly available.
We present a new form of ensemble method--Devil's Advocate, which uses a deliberately dissenting model to force other submodels within the ensemble to better collaborate. Our method consists of two different training settings: one follows the convent
ional training process (Norm), and the other is trained by artificially generated labels (DevAdv). After training the models, Norm models are fine-tuned through an additional loss function, which uses the DevAdv model as a constraint. In making a final decision, the proposed ensemble model sums the scores of Norm models and then subtracts the score of the DevAdv model. The DevAdv model improves the overall performance of the other models within the ensemble. In addition to our ensemble framework being based on psychological background, it also shows comparable or improved performance on 5 text classification tasks when compared to conventional ensemble methods.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
