Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Active In SP

Posts: 1
Joined: Feb 2010
04-02-2010, 03:58 PM


The idea of the DEAF MANâ„¢S TELEPHONE is a new way of designing a interactive telephone answering system. This paper is a development of our project and implimentation done in our college. Herein we introduce an interactive telephone answering system. This is particularly designed for Deaf man who cannot hear what the other person is speaking through the telephone. The processor converts the speech into text as readable to the deaf man. Speech recognition performance suffers from the involved nonlinear operations so that the greatly improved SNR often contrasts with only slight improvements in the recognition rate. Time-Frequency masking has emerged as a powerful technique for source separation of noisy and convolved speech mixtures. It has also been applied successfully for noisy speech recognition. Here, another approach is suggested for source separation, which estimates sufficient statistics for speech features in the preprocessing (e.g. STFT-)domain, propagates these statistics through the transforms from the spectrum to e.g. the MFCCâ„¢s of a speech recognition system and uses the estimated statistics for missing data speech recognition. With this approach, significant gains can be achieved in speech recognition rates, and in this context, time-frequency masking yields recognition rate improvements of more than 35% when compared to TF-masking based source separation. This paper describes a single chip speech recognition system. We use 10th order cepstrum coefficients and log-scaled energy as the feature vectors and Discrete Hidden Markov Model (DHMM) as recognition tool.
chinnu nani
Active In SP

Posts: 5
Joined: Feb 2010
04-02-2010, 04:39 PM

Active In SP

Posts: 291
Joined: Apr 2010
04-04-2010, 09:04 PM

Speech Recognition With TMS320C31 and SPOX
The above application requires conversion of speech into text which is done through speech recognition. The datasheet of the TMS320C31 decribes the following method:
Isolated word recognition:
limitations on previously
developed automatic speech recognition systems include limited vocabulary sets,
intolerance to even slight variations in speech, and inability to operate in real time.Artificial neural networks have been shown to perform pattern recognition, handle
incomplete data and variability very well. the salient features of
neural networks make them a useful tool in building better recognition systems for deaf
speech.Speech records were obtained from 6 deaf subjects.Speech intelligibility ratings were then obtained for each deaf speaker. The entire ASR system including the preprocessor, data set, feature extractor and the neural
network are implemented on the DSP TMS320C31. The software for pre-processing and recognition tasks was written in SPOX MI and C languages. to
incorporate the additional feature inputs to the network, A time delay neural
network model built for isolated digital recognition of normal speech was modified. time invariant feature extractors and
feature integrators were evolved by building time delays into the network.

Attached Files Thumbnail(s)

.pdf   Ultimate_Trends_in_Integrated_Systems_to_Enhance_Automatic_Speech_Recognition_Performance.pdf (Size: 633.88 KB / Downloads: 52)
Use Search at wisely To Get Information About Project Topic and Seminar ideas with report/source code along pdf and ppt presenaion

Important Note..!

If you are not satisfied with above reply ,..Please


So that we will collect data for you and will made reply to the request....OR try below "QUICK REPLY" box to add a reply to this page

Quick Reply
Type your reply to this message here.

Image Verification
Please enter the text contained within the image into the text box below it. This process is used to prevent automated spam bots.
Image Verification
(case insensitive)

Possibly Related Threads...
Thread Author Replies Views Last Post
  pdf design review of any product system strength and rigidity consideration Guest 2 144 12-01-2017, 07:56 PM
Last Post: Guest
  ecg signal denoising using median filter matlab code Guest 1 83 31-10-2016, 03:03 PM
Last Post: amrutha735
  xls flash mixer design in water treatment plant Guest 1 93 31-10-2016, 02:36 PM
Last Post: jaseela123
  dsp multiple choice questions and answers ppt Guest 1 74 31-10-2016, 01:59 PM
Last Post: jaseela123
  design of overhead rectangular water tank xls Guest 1 136 31-10-2016, 01:17 PM
Last Post: amrutha735
  case study of one patent from the product design point of view ppt on automobile Guest 1 511 31-10-2016, 12:21 PM
Last Post: amrutha735
  design of rcc lintel beam with chajja as per is456 Guest 1 128 31-10-2016, 12:06 PM
Last Post: jaseela123
  design and fabrication of accident preventing system in cutting machine Guest 1 82 31-10-2016, 10:39 AM
Last Post: ijasti
  pdf design review of any product system strength and rigidity consideration Guest 1 306 31-10-2016, 10:30 AM
Last Post: jaseela123
  ppt file of bell crank lever design Guest 1 140 31-10-2016, 09:33 AM
Last Post: jaseela123