Latent Prosody Model of Continuous Mandarin Speech

Several neural network-based tone recognition schemes for continuous Mandarin speech are discussed. A basic MLP tone recognizer using recognition features extracted from the processing syllable is first introduced. Then, some additional features extracted from neighboring syllables are added to compensate for the coarticulation effect. It is then further improved to compensate For the effect of sandhi rules of tone pronunciation by including tone information of neighboring syllables. The recognition criterion is now changed to find the best tone sequence that minimizes the total risk that simultaneously considers tone recognition of all syllables in the input utterance. Last, two approaches using HCNN and HSMLP, respectively, to model the intonation pattern as a hidden Markov chain for assisting tone recognition are proposed. The effectiveness of these schemes was confirmed by simulations on a speaker-independent tone recognition task. A recognition rate of 86.72% was achieved. >

In Chinese languages, tones carry important information at various linguistic levels. This research is based on the belief that tone information, if acquired accurately and utilized effectively, contributes to the automatic speech recognition of Chinese. In particular, we focus on the Cantonese dialect, which is spoken by tens of millions of people in Southern China and Hong Kong. Cantonese is well known for its complicated tone system, which makes automatic tone recognition very difficult. This article describes an effective approach to explicit tone recognition of Cantonese in continuously spoken utterances. Tone feature vectors are derived, on a short-time basis, to characterize the syllable-wide patterns of F0 (fundamental frequency) and energy movements. A moving-window normalization technique is proposed to reduce the tone-irrelevant fluctuation of F0 and energy features. Hidden Markov models are employed for context-dependent acoustic modeling of different tones. A tone recognition accuracy of 66.4% has been achieved in the speaker-independent case. The recognized tone patterns are then utilized to assist Cantonese large-vocabulary continuous speech recognition (LVCSR) via a lattice expansion approach. Experimental results show that reliable tone information helps to improve the overall performance of LVCSR.

The automatic recognition of continuous English speech, as against isolated words, must contend with phonological processes at word boundaries that can distort the mapping between surface form and lexical entry. Past recognition systems have used generative phonological rules in a precompilation stage to expand the working dictionary. However, this greatly increases the bulk and complexity of the lexicon. It is also possible to use analytic rules to undo the putative effect of phonological processes at the time of recognition. However, this can lead to the postulation of nonwords and to slower processing times. A solution that blends the advantages of both approaches, with the disadvantages of neither, is to use finite state transducers (FSTs) as filters on permitted matchings between input strings and lexical entries. These were implemented in a recognition system, and found to increase the percentage of words recognized by three percentage points, at a cost of halving the signal‐to‐noise ratio, compared to the same system without phonological FSTs.

Use of fuzzy mathematical concepts in character spotting for automatic recognition of continuous speech in Hindi

Tonal languages, such as Chinese, use systematic variations of pitch to distinguish lexical or grammatical meaning. Thus, tone recognition is essential for tonal languages. Typically, tone recognition for isolated syllables involves three major steps: fundamental frequency (F0) detection, feature extraction, and classification. The work compares different techniques for these three steps and to answer the questions: for Mandarin Chinese syllables, what combination of fundamental frequency detection and feature extraction methods best prepare data for classification, and what is the most effective classification method for tone recognition. Three types of F0 detection methods (autocorrelation, cross-correlation and cepstrum), two feature extraction schemes (sampled F0 and average F0, slope and energy from three subsegments), four normalization methods (slope only, 0--100 scaled, z-score and T1 shift), and two classification methods (Support Vector Machine (SVM) and Multilayer Perceptron (MLP)) were experimentally studied using 700 collected data samples.

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.

Automatic recognition of continuous speech for small vocabularies (e.g., telephone or credit card digit sequences) is possible with excellent accuracy, even in applications using telephone lines and serving a large population of users. However, even such simple recognition tasks suffer decreased performance in adverse conditions, e.g., significant background noise or fading on portable telephone channels. If we further impose significant limitations on the computing resources for the recognition task, then robust efficient speech recognition is still a significant challenge, even for simple vocabularies. Since many practical recognition tasks take place over telephone lines and in conditions that are less than optimal, speech recognition must be robust. The traditional hidden Markov model approach to speech recognition, using cepstral analysis, is computationally intensive and often does not work well under adverse acoustic conditions. We examine a simpler spectral analysis method, and suggest a segmental approach. High recognition accuracy can be maintained, despite a large decrease in both memory and computation, compared to traditional approaches.

Since 1972, the Speech Recognition Group at IBM's Thomas J. Watson Research Center has worked on a system for the automatic recognition of natural continuous speech. The goal of our research is to produce a voice-activated text-processing system. We have recently worked on a 5,000-word isolated-speech system for recognition of business correspondence and interoffice memoranda.Although speech recognition is performed with beguiling ease by human beings, the task of transferring this ability to computers has proven quite difficult. Our approach to the problem has been to develop general statistical techniques that allow the recognition system to organize itself when presented with a large sample of speech called training data. In essence, our system refines itself from some crudely specified initial configuration so as to take advantage of regularities present in a speech sample.Suppose that a talker wishes to convey to a listener the string of words W1, W2, ..., Wn. Each of the words has a pronunciation, in accordance with which the talker will guide his/her speech apparatus through an intricate cascade of gestures, with the result that a series of sound pressure waves will emanate. A microphone placed within the influence of these waves will respond to them in a fashion that is characteristic of the word sequence W1, W2, ..., Wn.Let the response of the microphone be denoted by the sequence A1, ..., Am. We can regard A1, ..., Am as a garbled version of the intended message W1, ..., Wn. The problem of recovering a message from a garbled transmission is the province of communication theory. The problem may be stated as follows: for a garbled transmission A (=A1, ...Am), determine the message W (=W1, ..., Wn) that is most probable given A. That is, find W such that Pr(W|A) is as large as possible.From Bayes's rule, we have Pr(W|A) = {Pr(W|A)}Pr(W)}Pr(A). Since we are interested in maximizing this for a particular fixed A, we can ignore the denominator on the right. The first term in the numerator constitutes a probabilistic characterization of the transmission channel. It tells us what A's to expect when the talker intends a particular word string W. The second term in the numerator is a probabilistic characterization of the word strings that the talker desires to convey. Pr(W) embodies all rules of grammar (ungrammatical word strings are less probable than grammatical ones) as well as all semantic constraints (meaningless word strings are less probable than meaningful ones).It is, of course, impossible to compute these probabilities exactly. We have, however, developed methods for obtaining useful approximations to them. We refer to the approximation of Pr(A|W) as a statistical model for the speech production process and to the approximation of Pr(W) as a statistical model for the language. A discussion of these models constitutes the body of the talk.

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.

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.

Hybrid speech recognition systems incorporating deep neural networks (DNNs) with Hidden Markov Models/Gaussian Mixture Models have achieved good results. We propose applying various DNNs in automatic recognition of Russian continuous speech. We used different neural network models such as Convolutional Neural Networks (CNNs), modifications of Long short-term memory (LSTM), Residual Networks and Recurrent Convolutional Networks (RCNNs). The presented model achieved \(7.5\%\) reducing of word error rate (WER) compared with Kaldi baseline. Experiments are performed with extra-large vocabulary (more than 30 h) of Russian speech.