- You are here:
- Home
- Download
Search Results | Total Results found : 1196
You refine search by : All Results
We show an effective way of adding context information to shallow neural language models. We propose to use Subspace Multinomial Model (SMM) for context modeling and we add the extracted i-vectors in a computationally efficient way. By adding this information, we shrink the gap between shallow feed-forward network and an LSTM from 65 to 31 points of perplexity on the Wikitext-2 corpus (in the case of neural 5-gram model). Furthermore, we show that SMM i-vectors are suitable for domain adaptation and a very small amount of adaptation data (e.g. endmost 5% of a Wikipedia article) brings a substantial improvement. Our proposed changes are compatible
with most optimization techniques used for shallow feedforward LMs.
with most optimization techniques used for shallow feedforward LMs.
Added on December 19, 2018
348
More Details
- Contributed by : Individual
- Product Type : Research Paper
- License Type : Freeware
- System Requirement : Not Applicable
- Author : Karel Benes,Santosh Kesiraju,Lukas Burget
Nasals and approximants consonants are often confused with each other. Despite the distinction in the production mechanism, these two sound classes exhibit a similar low frequency behavior, and lack significant high frequency content. The present study uses a spectral representation obtained using the
zero time windowing (ZTW) analysis of speech, for the task of distinction between these two. The instantaneous spectral representation has good resolution at resonances, which helps to highlight the difference in the acoustic vocal tract system response for these sounds. The ZTW spectra around the regions of glottal closure instants are averaged to derive parameters for their classification in continuous speech.
zero time windowing (ZTW) analysis of speech, for the task of distinction between these two. The instantaneous spectral representation has good resolution at resonances, which helps to highlight the difference in the acoustic vocal tract system response for these sounds. The ZTW spectra around the regions of glottal closure instants are averaged to derive parameters for their classification in continuous speech.
Added on December 19, 2018
35
More Details
- Contributed by : Individual
- Product Type : Research Paper
- License Type : Freeware
- System Requirement : Not Applicable
- Author : RaviShankar Prasad,Sudarsana Reddy Kadiri,Suryakanth V. Gangashetty,B. Yegnanarayana
Impulse-like characteristics of excitation occur at the glottal closure instant (GCI) due to sharp closure of the vibrating vocal folds in each glottal cycle. The GCIs are detected from the excitation component of the speech signal, and the excitation component is derived using inverse filtering or its variants. In this paper we propose a method for GCI detection based on single frequency filtering (SFF) of the speech signal. The SFF output has high signal-to-noise ratio (SNR) property in speech regions. The variance (across frequency) contour computed from the SFF output show rapid changes around the GCIs, and these rapid changes can be observed even when the speech signal is degraded. Thus the GCI locations can be extracted even from degraded speech using the SFF analysis. The robustness of the method is demonstrated for several cases of degradation of speech signal.
Added on December 19, 2018
14
More Details
- Contributed by : Individual
- Product Type : Research Paper
- License Type : Freeware
- System Requirement : Not Applicable
- Author : G. Aneeja,Sudarsana Reddy Kadiri, B. Yegnanarayana
In this paper, a DNN based keyword spotting framework, that utilizes both spectral as well as prosodic information present in the speech signal, is proposed. A DNN is first trained to learn a set of hierarchical non-linear transformation parameters that project the original spectral and prosodic feature vectors onto a feature space where the distance between similar syllable pairs is small and between dissimilar syllable pairs is large. These transformed features are then fused using an attention based long short-term memory (LSTM) network. As a side result, a deep denoising autoencoder based fine-tuning technique is used to improve the performance of sequence predictions.
Added on December 19, 2018
96
More Details
- Contributed by : Individual
- Product Type : Research Paper
- License Type : Freeware
- System Requirement : Not Applicable
- Author : Laxmi Pandey, Karan Nathwani2
Many Inscript based standalone keyboard applications are available online for typing Punjabi but they are restrictive in nature and most of these do not offer formatting of the keyed-in content in the text area provided in the application. The main problem regarding these keyboard applications is that in the absence of an audio feedback for the keys pressed on the Punjabi Inscript keyboard, unless trained to use that keyboard, the visually impaired cannot make out whether the content is being typed correctly. In order to overcome this problem, we developed the Punjabi Unicode Inscript Keyboard with sound embedded on every keystroke. This keyboard can be used for typing directly in the Microsoft Word.
Added on December 19, 2018
76
More Details
- Contributed by : Individual
- Product Type : Research Paper
- License Type : Freeware
- System Requirement : Not Applicable
- Author : Ashish Batra,Dr. Suneet Madan
Please wait, we are processing your request...Toll Free number: 1800 209 1015
email: tdildc[at]cdac[dot]in
