NDLI: Segmental quasi-Bayesian learning of the mixture coefficients in SCHMM for speech recognition

Please wait, while we are loading the content...

Proceedings of ICSIPNN '94. International Conference on Speech, Image Processing and Neural Networks

Voice message summary for voice services

Ternary synaptic weights algorithm: neural network training with don't care attributes

Process identification using a modified Elman neural net

An application of the discrete Fourier transformation in simulating large neural networks

Comparison of three different architectures for MOS-compatible quadratic synapses

A design methodology of intelligent neuro-fuzzy system model using an improved max-min CRI method

Limited angle tomography using regularized extrapolation technique

An artificial neural network for tomographic reconstruction of time varying object

Generalization of hierarchical retinotopic networks using stochastic distortion models

Hough transform: it's application to the linearly moving point targets detection

On finite recurrent neural network

Blind deconvolution using a mixed projection-gradient approach

A novel algorithm for the restoration of AFM/STM images

A combined approach to enhancement of unknown blurred and noisy images

Adaptive median based multi-shell-order-statistics filters for the removal of impulsive noise

A solution to the dynamic range problem of pixel values in color image enhancement

Pyramidal hierarchical relaxation

Topology on image processing

Fast data-parallel rotation of digital volume images

Study and implement of parallel algorithms in image processing based on YH supercomputer

Training genetically evolving cellular automata for image processing

Iterative solutions of the linear least squares subject to linear constraints

Systolic array for binary multiplier

Optimal design of convex combinations for adaptive filtering with parallel signals

Spline wavelet packets and fast integral wavelet transform for the analysis of pressure and flow waves in arteries

Using localized basis function for multi-speaker speech recognition

A method for Chinese syllables recognition based upon sub-syllable hidden Markov model

Applying N-best keyword search to continuous speech recognition for telecommunication-based applications

An improved HMM/VQ training procedure for speaker-independent isolated word recognition

Corrective tuning by applying LVQ for continuous density and semi-continuous Markov models

A method for efficient DP matching in spoken word recognition

Performance comparison of several speech recognition methods

A general Chinese acoustic/phonetic decoder for syllable, word and continuous speech recognition

HMMs with mixtures of trend functions for automatic speech recognition

Contextual vector quantization for speech recognition with discrete hidden Markov model

Wavelet parameterization for speech recognition: variations in translation and scale parameters

Tree-based state clustering for large vocabulary speech recognition

Speaker adaptation through spectral transformation for HMM based speech recognition

Segmental quasi-Bayesian learning of the mixture coefficients in SCHMM for speech recognition

Stochastic language models for Chinese speech recognition based on Chinese spelling

The use of higher level linguistic knowledge for spelling-to-pronunciation generation

Transform domain adaptive processing with neural network controlled resonator banks

Double deconvolution using a neural network

Gabriel networks: self-organizing neural networks for adaptive vector quantization

A new vector quantization algorithm based on simulated annealing

Globally optimal vector quantizer design using stochastically competitive learning algorithm

Parameter estimation of a fractional Brownian motion in a white noise using wavelets

The fast algorithm for the finite length discrete wavelet transform

Scale space filtering by Fejer kernel

Application of fast integral wavelet transform to analysis of building vibration problems

An efficient pipelined VLSI implementation of rank order filter

Lipreadable frame animation driven by speech parameters

A comparative study of mixture-Gaussian VQ, ergodic HMMs and left-to-right HMMs for speaker recognition

A practical object oriented programming approach for implementing real-time speech compression algorithm

Confidence analysis for text-independent speaker identification: inspecting the effect of population size

Speaker normalization by input space optimization for continuous density hidden Markov models

Spectrograms of overlapping speech based upon instantaneous frequency

Efficient interconversion algorithm for PARCOR and LSP parameters

A speech-text retrieval system using semantic data of the English/Japanese conversational texts

Articulatory speech synthesis using a parametric model and a polynomial mapping technique

A comprehensive analysis, synthesis system and synthesis methodology for the production of high quality speech

Speech synthesis using two-sided linear prediction parameters

Research and implementation of text-to-speech system for Chinese

Text-to-speech system for Brazilian Portuguese using a reduced set of synthesis units

A comparison of acoustic and magnetic resonance imaging techniques in the estimation of vocal tract area functions

Articulatory control of a vocal tract model based on fractional delay waveguide filters

Novel quantization schemes for multi-pulse coder at 5 kbps

A robust and fast DP-CELP (double-pulse CELP) vocoder at the bit rate of 4 kb/s

Multiband excitation coding of speech at 2.0 kbps

A 6.6 kb/s CELP speech coder: high performance for GSM half-rate system

Improving the performance of long history scalar and vector LSP quantizers

Risk assessment of axillary lymph node metastases in early breast cancer patients using the maximum entropy network

Neural network technology for stock market index prediction

Solving least squares problems by neural network approach

Signal analysis of electromyogram by artificial neural network

CNN matching problem and applications

Novel 2-D Hough planes for the detection of ellipses

A coarse-to-fine approach for circle detection

Dynamic structuring of belief networks in a hierarchical perceptual organization

A new method for quadratic curve detection using K-RANSAC with acceleration techniques

A general framework for machine vision: hierarchical token grouping

Stability analysis and synthesis algorithm of bidirectional associative memory

On the quality of the solutions of the travelling salesman problem found by the Hopfield/Tank model

Comparative study of two neural network approaches for nonlinear identification

A dual-band excitation LSP codec for very low bit rate transmission

DCELP: a low bit rate and low delay speech coding method

Low delay CELP coding at 8 kbps using classified voiced and unvoiced excitation codebooks

A very low bit-rate matrix quantized speech coder with Gray coding

Subband ADPCM coding for wideband audio signals using analysis-by-synthesis quantization scheme

Handwritten character recognition by extended loop neural networks

Unstructured to structured error correction using neural nets

The interpolation property of fuzzy polynomial approximation

Finding elliptical shapes in an image using a pyramid architecture

A solution to the generalized Duda and Hart problem using Fourier parameterization

A new method of identifying occlusion and specular highlights using active vision

Estimation of the viewpoint of a single perspective projection image

A method for 3D surface reconstruction from range images

Some experiments on training multilayer feedforward neural networks of hard-limiting units using random weights

Autonomous hidden node determination using dynamic expansion and contraction approach

Nonlinear discriminant features constructed by using outputs of multilayer perceptron

An efficient scale and rotation invariant 2-D object recognition method

Parallel texture analysis using high-order statistics and neural networks

Super-high, scale invariant image compression using a surface learning neural network

Efficient supervised learning of multilayer feedforward neural networks

A theoretically sound learning algorithm for constructive neural networks

A homotopy recursive algorithm for multilayer feedforward neural network

FIST: fast iterative self-structuring and training of artificial neural networks

A robust and fast block motion estimation algorithm

Scalable multi-media information distribution architecture

Optimal bandwidth allocation of multiple VBR video sources with priorities

A novel method of motion estimation using luminance and chrominance blocks

Development of digital video systems in Taiwan

A theory on optimal construction of dynamic features of speech for HMM-based speech recognition

Noisy adaptive cepstral coefficients and its application to noisy speech recognition

Single channel adaptive noise cancelation for enhancing noisy speech

A speech separation system that is robust to reverberation

Speech recognition by extended loop neural network

Parallel neural networks for speaker-independent all-Chinese-syllable speech recognition

A neural network application for the analysis and synthesis of multilingual speech

A hybrid neural network/rule based architecture for diphone speech synthesis

A two-level model-based object recognition technique

Solutions of several color matching problems using convex projection theory

A comparison of multi-layer neural networks and optimized nearest neighbor classifiers for handwritten digit recognition

Fingerprint preclassification using key-points

A thresholding method using the mixture of normal density functions

A class of fractional random fields for image texture modelling

Autoregressive modelling through joint and weighted second and third order statistics

Cooperative fusion of stereo and motion

Efficient algorithms for interlaced to progressive scan conversion

The modelling of variable bit rate video traffic

Data association for multiple target tracking using Hopfield neural network

A multiresolution image matching algorithm for moving object detection by wavelets

Restoration of motion blurred images by MDL and piecewise constant image model

Recovery of the relative viewing distance of two views of an object under weak perspective projection

Moving target location by neighbour-search algorithm

Application of random and pseudo-random sampling for tracking moving objects

Modifications and performance improvements of 3-step search block-matching algorithm for video coding

Post-microphone-array speech enhancement with adaptive filters for forensic application

An eigendecomposition based two sided linear prediction model for robust speech recognition

LS algorithm to estimate FIR system using third and fourth order cumulants

Intelligibility of reverberant speech enhanced by inversion of room response

An initial independent and highly noise-resistant fuzzy possibilistic clustering algorithm

Recurrent sub neural networks applied to speech recognition

Transient responses in dynamical neural models

Chaos in recurrent networks

A neural network model for acquisition of semantic structures

Selection of key features for invariant object recognition using fuzzy entropy

Four Corner Code based pre-classification scheme for Chinese character recognition

A novel application of information theory to pattern recognition problems

3D object recognition using qualitative features

Vector quantization view of /spl Sigma//spl Delta/ modulation

Segment-oriented coding of textured images based on successive approximation

Finite state DCT with global bitmap image coding

Progressive image transmission using adaptive multistage vector quantization

Reference neighbourhood search (RNS) and its application in image coding

An adaptive pattern based image coding technique using visual pattern and texture pattern

A model for JPEG quantization

Using ANN for high speed iterated function system image compression

Rate/distortion in fractal compression: order of transform and block symmetries

A novel VQ encoding algorithm based on adaptive searching sequence

An improved JPEG image coder using the adaptive fast approximate Karhunen-Loeve transform (AKLT)

Golden Mandarin(II)-an intelligent Mandarin dictation machine for Chinese character input with adaptation/learning functions

Language processing for Chinese speech recognition

Recent advances in Japanese speech synthesis research

Corpus-based speech and language research in the Institute of Systems Science

The study on speech processing and character recognition at Telecommunication Laboratories (TL)

Current status and prospects of speech processing technology in Korea

From phonology and acoustic properties to automatic recognition of Cantonese

Speech recognition for Japanese spoken language

Phonetic and linguistic features of spoken Chinese

A hybrid neural network/rule based architecture used as a text to phoneme transcriber

Speech trajectory recognition in SOFM by using Bayes theorem

Tunable time delay neural networks for isolated word recognition

Connectionist models of categorical perception of speech

Classification of CV transitions in continuous speech using neural network models

Two iterative encoding schemes for bidirectional associative memory

Towards extending adaptive self-organizing concurrent system architecture

Fast self-organization by query-based algorithm and its applications

Convergence of one-dimensional self-organizing map

On MNCP in two-stage technique for 3D camera calibration for machine vision metrology

Computer graphics animations of talking faces based on stochastic models

Automatic positioning of reference systems of radiographic images

An architecture for a knowledge-based image inspection system

An algorithm for single-pixel detection and tracking

Progressive edge extraction using multistage predictive coding

Extraction of the focused object in an image by filtering out the defocused background

Generalized threshold decomposition

A new method for multilevel thresholding using symmetry and duality of the histogram

Precision tracking of overlapping small targets

Edge detection on real time using LOG filter

A new look at finite mixture models in medical image analysis

Image segmentation using maximum entropy method

Segment the metallograph images using Gabor filter

A new edge detection algorithm based on a statistical approach

Locating head boundary by snakes

Self-organization grouping for feature extraction and image segmentation

Shape characterization and its applications

Finding of optimal morphological filter on binary images based on greedy and branch & bound searching

Computer texture boundary detection based on human visual perception model

Advances in image/video signal processing

Human computer interactions using language based technology

Proceedings of ICSIPNN '94. International Conference on Speech, Image Processing and Neural Networks

Segmental quasi-Bayesian learning of the mixture coefficients in SCHMM for speech recognition

Content Provider	IEEE Xplore Digital Library
Author	Qiang Huo Chorkin Chan Chin-Hui Lee
Copyright Year	1994
Description	Author affiliation: Dept. of Comput. Sci., Hong Kong Univ., Hong Kong (Qiang Huo; Chorkin Chan)
Abstract	A theoretical formulation of the segmental quasi-Bayes learning of mixture coefficients in semi-continuous hidden Markov models (SCHMM) is presented. Its viability is confirmed by a series of comparative experiments using different adaptive training algorithms in estimating the mixture coefficients of the SCHMM for speaker adaptation (SA) application. Despite the fact that a batch (or block) adaptation scheme is adopted in this study, the proposed segmental quasi-Bayes method is also very suitable for performing an incremental (or on-line) adaptation of the HMM parameters, in view of its sequential nature in updating both the hyper-parameters of the prior distribution and the mixture coefficients themselves.<>
Starting Page	678
Ending Page	681
File Size	355637
Page Count	4
File Format	PDF
ISBN	078031865X
DOI	10.1109/SIPNN.1994.344820
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	1994-04-13
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Computer science Parameter estimation Bayesian methods Hidden Markov models Speech recognition Bismuth Probability density function Covariance matrix Decoding State estimation
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in