Hierarchical speech recognition system using MFCC feature extraction and dynamic spiking RSOM

In this paper, we propose a system of a tree evolutionary recurrent self-organizing models. Inherited from the Growing Hierarchical Self-Organizing Map GHSOM. The proposed GHSOM variants are characterized by a hierarchical model, composed of independent RSOMs (recurrent Self-Organizing Map). The case study of the proposed system is phoneme recognition in continuous speech and speaker independent context. GHSOM variants serve az tools for developing intel- ligent systems and proposed artificial intelligence application.

Segmentation of gray level images into regions of uniform texture is investigated. An unsupervised approach through the use of Kohonen's self organizing map (SOM) and a multilayer version of it, the hierarchical self organizing map (HSOM), is employed to find the regions in an image composed of textures from different classes. For testing, gray level artificial textured images modeled as Markov random fields are used as the input. No parameter estimation is done. The size and the topology of SOM and HSOM are independent from the size of the input image. The segmentation results are very promising.

Studies the problem of phonetic modeling for continuous Mandarin speech recognition by providing a systematic performance comparison for systems based on following primitive speech units: syllables, demi-syllables (initial and final), context-independent phones, left-or-right context-dependent phones (diphones) and left-and-right context-dependent phones (triphones). In our speaker-dependent continuous speech recognition experiments, a generalized triphone system has achieved the best performance of all. Our best system is in contrast to most other Mandarin speech recognition systems, which have been based on demi-syllable units.

The application of hierarchical self organizing maps (HSOM) to the segmentation of cell migration images, obtained during high-content screening in molecular medicine, is described. The segmentation is critical to our larger project for developing methods for the automatic annotation of cell migration images. The HSOM appears to perform better than the conventional computer-vision methods of histogram thresholding, edge detection, and the newer techniques involving single-layer SOMs. However, the HSOM techniques have to be complemented by region-based techniques to improve the quality of the segmented images.

For extra-large vocabulary continuous speech recognition a language model that describes permissible phrases is needed. In the paper, the results of experiments on extra-large vocabulary (above 100 K words) continuous speech recognition, with usage of n-gram models, are presented. A quantitative comparison of recognition accuracy of words, symbols, and phonemes depending on n-gram model, with n value varying from 0 till 3, was made.

The authors present an NN-IIR (neural network/infinite impulse response filter) system for phoneme recognition in continuous speech based on the idea of modeling the recognition process by state evolution and interpretation equations. This work gives a solution to temporal information representation in phoneme recognition using neural networks and recursive filters, yielding better recognition results for continuous speech. This recognition system has two promising properties, i.e., capabilities for dealing with sequential properties and for interpreting speech signals by means of a training process. It was shown experimentally that the NN-IIR network obtained good performance for continuous speech recognition. Preliminary experiments with limited training data indicate that the NN-IIR provides good discrimination power for plosives, which are highly context-dependent.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

A connectionist structure for phoneme recognition in continuous speech is described. This has two main parts. The first is a sound subunit classifier in the form of a three-layer back propagation network which classifies speech subunits from frames of spectral speech data. This is followed by a sequence classifier in the form of a network of neural like-units which classifies phonemes from input sequences of subunits by their occurrence and duration. Results are given for a 15-phoneme subset of British English, for a single speaker. These include the difficult syllable initial and final stop consonants, fricatives, vowels, and diphthongs. The overall recognition accuracy achieved is 87%. >

Continuous speech is far more natural and efficient than isolated speech for communication. However, for current state-of-the-art automatic speech recognition systems, isolated speech recognition (ISR) is far more accurate than continuous speech recognition (CSR). It is common practice in the speech research community to build CSR systems using only CS data. However, slowing of the speaking rate is a natural reaction for a user faced with the high error rates of current CSR systems. Ironically, CSR systems typically have a much higher word error rate when speakers slow down since the acoustic models are usually derived exclusively from continuous speech corpora. In this paper, we summarize our efforts to improve the robustness of our speaker-independent CSR system against speaking styles, without suffering a recognition accuracy penalty. In particular the multi-style trained system described in this paper attains a 7.0% word error rate for a test set consisting of both isolated and continuous speech, in contrast to the 10.9% word error rate achieved by the same system trained only on continuous speech.

The choice of basic modeling unit in building acoustic model for a continuous Mandarin speech recognition task is a very important issue [1]. Unlike traditional phoneme or Initial/Finals (IFs) units based acoustic modeling methods, which usually suffer from the limitations of less accuracy in modeling intrasyllable variations and long scale temporal dependencies, in this paper, a practicable syllable based approach is presented. In contrast with IFs, syllable can implicitly model the intrasyllable variations in good accuracy. Also, by carefully choosing context modeling schemes and parameter tying methods, syllable based acoustic model can capture longer temporal variations while keeping the complexity of model well controlled. Meanwhile, considering the data unbalanced problem, multiple sized unit model based approaches are also implemented in this research. The experiment result shows the acoustic model based on the presented syllable based approach is effective in improving the performance of the Chinese continuous speech recognition.

Automatic disorders recognition in speech can be very helpful for a therapist while monitoring therapy progress of patients with disordered speech. This article is focused on sound repetitions. The signal is analyzed using Continuous Wavelet Transform with 16 bark scales. Using the silence finding algorithm, only speech fragments are automatically found and cut. Each cut fragment is converted into a fixed-length vector and passed into the Kohonen network. Finally, the Kohonen winning neuron result is put on the 3-layer perceptron. Most of the analysis was performer and the results were obtained using the authors’ program WaveBlaster. We use the STATISTICA package for finding the best perceptron which was then imported back into WaveBlaster and used for automatic blockades finding. The problem presented in this article is a part of our research work aimed at creating an automatic disordered speech recognition system.

Inherent features of the Bangla (widely used as Bengali) language like long and short vowels and many instances of allophones make it difficult to build a continuous speech recognizer for the language. Stress and accent vary in spoken Bangla language from region to region. But in formal read Bangla speech, stress and accents are ignored. There are three approaches to continuous speech recognition (CSR) based on the sub-word unit viz. word, phoneme and syllable. Pronunciation of words and sentences are strictly governed by set of linguistic rules. Many attempts have been made to build continuous speech recognizers for Bangla for small and restricted tasks. However, medium and large vocabulary CSR for Bangla is relatively new and not explored. In this paper, the authors have attempted for extracting local features (LFs) from a Bangla input speech for tri-phone based automatic speech recognition (ASR) method. The method comprises two stages, where the first stage extracts LFs from input speech and the final stage generates word strings based on trip hone hidden Markov models (HMMs). The objective of this research is to build a medium vocabulary trip hone based continuous speech recognizer for Bangla language by extracting LFs over mel frequency cepstral coefficients (MFCCs). In this experimentation using Bangla speech corpus prepared by us, the recognizer provides higher word accuracy, word correct rate as well as sentence correct rate for trained and tested sentences with fewer mixture components in HMMs.

Algorithms for speech recognition can be characterized broadly as pattern recognition approaches and acoustic phonetic approaches. To date, the greatest degree of success in speech recognition has been obtained using pattern recognition paradigms. Thus, in this paper, we will be concerned primarily with showing how pattern recognition techniques have been applied to the problems of isolated word (or discrete utterance) recognition, connected word recognition, and continuous speech recognition. We will show that our understanding (and consequently the resulting recognizer performance) is best for the simplest recognition tasks and is considerably less well developed for large scale recognition systems.

The authors argue that a more complete understanding of how people produce and comprehend language will require investigating real-time spoken-language processing in natural tasks, including those that require goal-oriented unscripted conversation. One promising methodology for such studies is monitoring eye movements as speakers and listeners perform natural tasks. Three lines of research that adopt this approach are reviewed: (i) spoken word recognition in continuous speech, (ii) reference resolution in real-world contexts, and (iii) real-time language processing in interactive conversation.

In this paper, we propose two architectural variants of our recent adaptation of a ‘few shot-learning’ (FSL) framework ‘Matching Networks’ (MN) to end-to-end (E2E) continuous speech recognition (CSR) in a formulation termed ‘MN-CTC’ which involves a CTC-loss based end-to-end episodic training of MN and an associated CTC-based decoding of continuous speech. An important component of the MN theory is the labelled support-set during training and inference. The architectural variants proposed and studied here for E2E CSR, namely, the ‘Uncoupled MN-CTC’ and the ‘Coupled MN-CTC’, address this problem of generating supervised support sets from continuous speech. While the ‘Uncoupled MN-CTC’ generates the support-sets ‘outside’ the MN-architecture, the ‘Coupled MN-CTC’ variant is a derivative framework which generates the support set ‘within’ the MN-architecture through a multi-task formulation coupling the support-set generation loss and the main MN-CTC loss for jointly optimizing the support-sets and the embedding functions of MN. On TIMIT and Librispeech datasets, we establish the ‘few-shot’ effectiveness of the proposed variants with PER and LER performances and also demonstrate the cross-domain applicability of the MN-CTC formulation with a Librispeech trained ‘Coupled MN-CTC’ variant inferencing on TIMIT low resource target-corpus with a 8% (absolute) LER advantage over a single-domain (TIMIT only) scenario.

The main objective of this paper is to explore the effectiveness of perceptual features for performing isolated digits and continuous speech recognition. The proposed perceptual features are captured and code book indices are extracted. Expectation maximization algorithm is used to generate HMM models for the speeches. Speech recognition system is evaluated on clean test speeches and the experimental results reveal the performance of the proposed algorithm in recognizing isolated digits and continuous speeches based on maximum log likelihood value between test features and HMM models for each speech. Performance of these features is tested on speeches randomly chosen from “TI Digits_1”, “TI Digits_2” and “TIMIT” databases. This algorithm is tested for VQ and combination of VQ and HMM speech modeling techniques. Perceptual linear predictive cepstrum yields the accuracy of 86% and 93% for speaker independent isolated digit recognition using VQ and combination of VQ & HMM speech models respectively. This feature also gives 99% and 100% accuracy for speaker independent continuous speech recognition by using VQ and the combination of VQ & HMM speech modeling techniques.