New directions in automatic speech recognition: a communication perspective

In this paper, we describe the statistical approach to text translation. Starting from the Bayes decision rule as in speech recognition, we study the translation problem and present algorithms for tackling the translation task. The statistical translation approach uses two types of information: a translation model and a language model. The language model used is a bigram or trigram model as in speech recognition. The translation model is decomposed into a lexicon model and an alignment model. The alignment model is similar to the time alignment problem in speech recognition. After presenting the details of the alignment model, we describe the search problem and present suitable search algorithms, namely an iterative search method and a dynamic programming based method.

The EMIME European project is conducting research in the development of technologies for mobile, personalised speech-tospeech translation systems. The hidden Markov model is being used as the underlying technology in both automatic speech recognition (ASR) and text-to-speech synthesis (TTS) components, thus, the investigation of unified statistical modelling approaches has become an implicit goal of our research. As one of the first steps towards this goal, we have been investigating commonalities and differences between HMM-based ASR and TTS. In this paper we present results and analysis of a series of experiments that have been conducted on English ASR and TTS systems measuring their performance with respect to phone set and lexicon, acoustic feature type and dimensionality andHMM topology. Our results show that, although the fundamental statistical model may be essentially the same, optimal ASR and TTS performance often demands diametrically opposed system designs. This represents a major challenge to be addressed in the investigation of such unified modelling approaches.

Recent approaches in statistical modeling on fisheries research have focused on addressing the relationship between fish catch per unit effort (CPUE) data and remotely sensed oceanographic data. This study used multiple statistical modeling approaches to ensure a satisfied result in determining the most important parameter that influences the CPUE distribution of Rastrelliger kanagurta. Oceanographic data including water depth (WD), chlorophyll-a (CHL), sea surface temperature (SST), sea surface height (SSH) and surface wind (SW) are the environmental parameters which were extracted from 570 locations within EEZ of Malaysia by using GIS techniques. The combination of CPUE and oceanographic data was analyzed and then fitted simultaneously in each performance of Generalized Additive Model (GAM), Generalized Linear Model (GLM), Boosted Regression Tree (BRT) and Multivariate Adaptive Regression Splines (MARS). Each statistical modeling approach resulted difference ways to describe the relationship between fish and its environment. Results showed the non-linear behavior fish CPUE having the strongest overall relationship with SSH as SSH was always at the top. This indicated that SSH was the most important parameter affecting CPUE based on the highest percentage of relative influence and variable importance with great significant relationship (p<0.001) compared to other parameters. This study showed the capability of GIS and statistical modeling to understand the R. kanagurta distribution and its environment parameters in South China Sea.

The Relative Distance Vector Neural Network (RDVNN) Model: A Hybrid Approach to Speech Recognition

: This thesis examines the acoustic-modeling problem in automatic speech recognition from an information-theoretic point of view. This problem is to design a speech-recognition system which can extract from the speech waveform as much information as possible about the corresponding word sequence. The information extraction process is broken down into two steps: a signal processing step which converts a speech waveform into a sequence of information bearing acoustic feature vectors, and a step which models such a sequence. This thesis is primarily concerned with the use of hidden Markov models to model sequences of feature vectors which lie in a continuous space such as R sub N. It explores the trade-off between packing a lot of information into such sequences and being able to model them accurately. The difficulty of developing accurate models of continuous parameter sequences is addressed by investigating a method of parameter estimation which is specifically designed to cope with inaccurate modeling assumptions.

A high performance neural-network-based speech recognition system is presented. A new approach towards feature representation for speech recognition, named state transition matrix (STM), is proposed to address temporal varying problem in speech recognition. Using STM, we need only a single-layer perceptron neural network to perform speech recognition. Experimental results show that an overall accuracy of 95% and 87% was achieved for speaker-dependent isolated word recognition and multi-speaker-dependent isolated word recognition, respectively.

In this paper, we present a new technique for social mobile robot speech recognition based on scene-associated training models. The key contribution of the paper is a real-time framework that reduces the effect of room reverberation and ambient noise, a challenging problem in speech recognition. In classical approaches, anechoic sound is used to train the model, with the main focus on removing reverberation or noise from the sound. Our technique differs in that we train a number of speech recognizers directly from the reverberated sound, by associating each recognizer with a unique visual scene, to deal with the varying reverberation properties of different rooms. By extracting local features from a captured image and recognizing a scene, the robot can use the appropriate speech recognizer that is trained for the particular structural properties of that scene. We tested our method by using a baseline speech recognition model (HTK) across a variety of rooms and different levels of background noise. The results show that the association between a visual scene and a corresponding speech recognizer greatly improves the robot's speech recognition accuracy, together with increasing the computational speed of recognition, compared to competing techniques.

A model-based framework of classification error rate estimation is proposed for speech and speaker recognition. It aims at predicting the run-time performance of a hidden Markov model (HMM) based recognition system for a given task vocabulary and grammar without the need of running recognition experiments using a separate set of testing samples. This is highly desirable both in theory and in practice. However, the error rate expression in HMM-based speech recognition systems has no closed form solution due to the complexity of the multi-class comparison process and the need for dynamic time warping to handle various speech patterns. To alleviate the difficulty, we propose a one-dimensional model-based misclassification measure to evaluate the distance between a particular model of interest and a combination of many of its competing models. The error rate for a class characterized by the HMM is then the value of a smoothed zero-one error function given the misclassification measure. The overall error rate of the task vocabulary could then be computed as a function of all the available class error rates. The key here is to evaluate the misclassification measure in terms of the parameters of environmental-matched models without running recognition experiments, where the models are adapted by very limited data that could be just the testing utterance itself. In this paper, we show how the misclassification measure could be approximated by first computing the distance between two mixture Gaussian densities, then between two HMMs with mixture Gaussian state observation densities and finally between two sequences of HMMs. The misclassification measure is then converted into classification error rate. When comparing the error rate obtained in running actual experiments and that of the new framework, the proposed algorithm accurately estimates the classification error rate for many types of speech and speaker recognition problems. Based on the same framework, it is also demonstrated that the error rate of a recognition system in a noisy environment could also be predicted.

This study investigates the influence of service quality on tourist revisit intentions in the culturally rich state of Rajasthan, India, employing a comprehensive statistical and mathematical modeling approach. As the tourism sector increasingly drives economic growth and cultural exchange, understanding the factors that encourage revisits is essential for sustainable tourism development. This paper develops a predictive framework that integrates service quality dimensions with revisit intentions, utilizing data collected from tourists across key destinations such as Jaipur, Udaipur, and Jodhpur. Using a structured questionnaire, the study gathers perceptions of service quality based on the SERVQUAL model, which includes tangibles, reliability, responsiveness, assurance, and empathy. The data undergo rigorous statistical analysis, employing multivariate techniques such as factor analysis to refine the service quality dimensions and structural equation modeling (SEM) to explore the causal relationships between service quality and revisit intentions. The study uniquely applies a mixed-effects model to account for the variability across different cities and tourist experiences, enhancing the generalizability of the findings. Findings suggest that among the service quality dimensions, 'assurance' and 'empathy' have the most significant impact on revisit intentions, indicating that trust and emotional connection are crucial for repeat tourism. The paper discusses the implications of these results for tourism marketers and policymakers, emphasizing targeted strategies to enhance customer satisfaction and loyalty. Additionally, the study contributes to the existing literature by validating the applicability of the SERVQUAL model in the context of Rajasthan's tourism industry and expanding it through mathematical modeling techniques. This research not only aids in theoretical advancements in tourism studies but also provides practical insights for improving service quality to boost Rajasthan's appeal as a repeat tourist destination.

Rib cage 3D reconstruction is an important prerequisite for thoracic spine modelling, particularly for studies of the deformed thorax in adolescent idiopathic scoliosis. This study proposes a new method for rib cage 3D reconstruction from biplanar radiographs, using a statistical parametric model approach. Simplified parametric models were defined at the hierarchical levels of rib cage surface, rib midline and rib surface, and applied on a database of 86 trunks. The resulting parameter database served to train statistical models which were used to quickly provide a first estimate of the reconstruction from identifications on both radiographs. This solution was then refined by manual adjustments in order to improve the matching between model and image. Accuracy was assessed by comparison with 29 rib cages from CT scans in terms of geometrical parameter differences and in terms of line-to-line error distance between the rib midlines. Intra and inter-observer reproducibility was determined for 20 scoliotic patients. The first estimate (mean reconstruction time of 2 min 30 s) was sufficient to extract the main rib cage global parameters with a 95% confidence interval lower than 7%, 8%, 2% and 4° for rib cage volume, antero-posterior and lateral maximal diameters and maximal rib hump, respectively. The mean error distance was 5.4 mm (max 35 mm) down to 3.6 mm (max 24 mm) after the manual adjustment step (3 min 30 s). The proposed method will improve developments of rib cage finite element modelling and evaluation of clinical outcomes.

Introduction The ability to perceive and comprehend speech is, as we argued in the previous chapter, one of the human brain's more astonishing evolutionary accomplishments. Engineers and computer scientists have sought to emulate human speech recognition for about four decades, but it may be as many more before the best automatic speech recognition device can perform as well as the average five-year-old, though great strides have been made in recent years. Recognizing speech and the identity of the speaker is an ability that we normally take for granted, unless we are unfortunate enough to lose this vital skill temporarily or permanently as the result of ‘a stroke’ (cerebrovascular accident) or some other form of damage to language-critical areas of the brain. In this and the following two chapters we will be concerned with the early or peripheral stages of spoken language comprehension: with auditory signal processing; with the extraction of phonetic features that make up the ‘sound shapes’ of words; with how the phonological forms of words are retrieved from lexical memory and how these ‘sound traces’ of words may be represented in the recognition lexicon. We will leave to later chapters questions of how words are put together to form phrases or sentences, which belong to later stages of the spoken language comprehension process.

Learning sets of filters using back-propagation

We show the effect of reverberation on the speech recognition performance in a far-field microphone. Given the reference of a close-talk microphone signal, an improvement is shown using an asymmetric non-causal inverse filter both in a synthetic and real room environment. Its variants in time and frequency domain are also presented and compared with other existing techniques. We argue for the approaches which specifically consider recognition performance as a goal in deriving the dereverberating schemes, with evaluation on real room recording recognition, as a future direction for solving reverberation problems in speech recognition.

The performance of current speech recognition systems is far below that of humans. Neural nets offer the potential of providing massive parallelism, adaptation, and new algorithmic approaches to problems in speech recognition. Initial studies have demonstrated that multilayer networks with time delays can provide excellent discrimination between small sets of pre-segmented difficult-to-discriminate words, consonants, and vowels. Performance for these small vocabularies has often exceeded that of more conventional approaches. Physiological front ends have provided improved recognition accuracy in noise and a cochlea filter-bank that could be used in these front ends has been implemented using micro-power analog VLSI techniques. Techniques have been developed to scale networks up in size to handle larger vocabularies, to reduce training time, and to train nets with recurrent connections. Multilayer perceptron classifiers are being integrated into conventional continuous-speech recognizers. Neural net architectures have been developed to perform the computations required by vector quantizers, static pattern classifiers, and the Viterbi decoding algorithm. Further work is necessary for large-vocabulary continuous-speech problems, to develop training algorithms that progressively build internal word models, and to develop compact VLSI neural net hardware.

Problems in speech recognition are often apparent in telecommunication situations. For ecologically valid assessments of such conditions, it is important to quantify the impact of real environments including acoustic conditions at a far-end communication device and all paths of transmission degradation. This study presents an automated matrix sentence test procedure based on automatic speech recognition (ASR) integrated in a Voice over Internet Protocol (VoIP) infrastructure and compares the individual effects of transmission degradations with results from laboratory measurements. Speech recognition thresholds (SRTs) were measured in 16 normal-hearing subjects in four test conditions: (a) a laboratory condition guided by a human experimenter, (b) a laboratory condition with reduced bandwidth and (c) additionally reduced headset quality to simulate typical communication systems, and (d) an automated, ASR-controlled adaptive test procedure over a real VoIP infrastructure. Errors of the ASR system were analyzed to show possible effects on measurement outcome Results: Measured SRTs showed a highly significant correlation (r = .93) between the fully automatic and "laboratory" conditions, with a constant bias of about 1 dB indicating a linear shift of the data without affecting the distribution around the mean. The individual impact of the different system degradations on SRTs could be quantified Conclusions: This study provides a proof of concept for automated ASR-based SRT measurements over VoIP systems for speech audiometric testing in real communication systems, as it produced results comparable to traditional laboratory settings for this group of 16 normal-hearing subjects. This makes VoIP services a promising candidate for speech audiometric testing in real communication systems.