Applications of voice processing to telecommunications

The ways in which people communicate are changing rapidly. The options are many and diverse, ranging from voice calls over wireless networks, to video calls over the conventional wired network, ISDN video, FAX, e-mail, voice mail, beeper services, data services, audio teleconferencing, video teleconferencing, and so-called scribble phone service (transmission of arbitrary handwritten input). This revolution in communications is being fueled by several sources, including the availability of low-cost, low-power, computation in both DSP and RISC chips, larger and cheaper memory chips, improved algorithms for communications (e.g., modems, signaling) and signal processing, and finally the creation of world-wide standards for transmission, signal compression, and communication protocols. The broad goal of the communications revolution is to provide seamless and high-quality communications between people (or groups of people), anywhere, anytime, and at a reasonable price. Although there are many technologies that form the bases for the communications environment of the twenty-first century, one of the key technologies for making the vision a reality is voice processing. In this paper we attempt to show, by example, how voice processing has been applied to specific problems in telecommunications, and how it will grow to become an even more essential component of the communications systems of the twenty-first century     

Training set design for connected speech recognition

Two methods for generating training sets for a speech recognition system are studied. The first uses a nondeterministic statistical method to generate a uniform distribution of sentences from a finite state machine (FSM) represented in digraph form. The second method, a deterministic heuristic approach, takes into consideration the importance of word ordering to address the problem of coarticulation effects. The two methods are critically compared. The first algorithm, referred to as MARKOV, converts the FSM into a first-order Markov model. The digraphs are determined, transitive closure computed, transition probabilities are assigned, and stopping criteria established. An efficient algorithm for computing these parameters is described. Statistical tests are conducted to verify performance and demonstrate its utility. A second algorithm for generating training sentences, referred to as BIGRAM, uses heuristics to satisfy three requirements: adequate coverage of basic speech (subword) units; adequate coverage of words in the recognition vocabulary (intraword contextual units); and adequate coverage of word pairs bigrams (interword contextual units)     

A model-based connected-digit recognition system using either hidden Markov models or templates

Although a great deal of effort has gone into studying large-vocabulary speech-recognition problems, there remains a number of interesting, and potentially exceedingly important, problems which do not require the complexity of these large systems. One such problem is connected-digit recognition, which has applications to telecommunications, order entry, credit-card entry, forms automation, and data-base management, among others. Connected-digit recognition is also an interesting problem for another reason, namely that it is one in which whole-word training patterns are applicable as the basic speech-recognition unit. Thus one can bring to bear all the fundamental speech recognition technology associated with whole-word recognition to solve this problem. As such, several connected digit recognizers have been proposed in the past few years. The performance of these systems has steadily improved to the point where high digit-recognition accuracy is achievable in a speaker-trained mode.In this paper we present a unified system for automatically recognizing fluently spoken digit strings based on whole-word reference units. The system that we will describe can use either hidden Markov model (HMM) technology or template-based technology. In fact the overall system contains features from both approaches.A key factor in the success of the various connected digit recognizers is the ability to derive, via a training procedure, a good set of representations of the behavior of the individual digits in actual connected digit strings. For most applications, isolated digit training does not provide a good enough characterization of the variability of the digits in strings. The “best” training procedure is to derive the digit reference patterns (either templates or statistical models) from connected digit strings. Such a connected word training procedure, based on a segmental k-means loop, has been proposed and was tested on seven experienced users of speech recognizers. For these seven talkers, average string accuracies of greater than 98% for unknown length strings, and greater than 99% for known length strings were obtained on an independent test set of 525 variable length strings (1–7 digits) recorded over local dialed-up telephone lines.To evaluate the performance of the overall connected digit recognizer under more difficult conditions, a set of 50 people (25 men, 25 women), from the non-technical local population, was each asked to record 1200 random digit strings over local dialed-up telephone lines. Both a speaker-trained and a multi-speaker training set was created, and a full performance evaluation was made. Results show that the average string accuracy for unknown- and known-length strings, in the speaker-trained mode, was 98% and 99% respectively; in the multi-speaker mode the average string accuracies were 94% and 96.6% respectively. A complete analysis of these results is given in this paper.     

The ecological effects of universal and selective violence prevention programs for middle school students: A randomized trial.

This study reports the findings of a multisite randomized trial evaluating the separate and combined effects of 2 school-based approaches to reduce violence among early adolescents. A total of 37 schools at 4 sites were randomized to 4 conditions: (1) a universal intervention that involved implementing a student curriculum and teacher training with 6th-grade students and teachers, (2) a selective intervention in which a family intervention was implemented with a subset of 6th-grade students exhibiting high levels of aggression and social influence, (3) a combined intervention condition, and (4) a no-intervention control condition. Analyses of multiple waves of data from 2 cohorts of students at each school (N = 5,581) within the grade targeted by the interventions revealed a complex pattern. There was some evidence to suggest that the universal intervention was associated with increases in aggression and reductions in victimization; however, these effects were moderated by preintervention risk. In contrast, the selective intervention was associated with decreases in aggression but no changes in victimization. These findings have important implications for efforts to develop effective violence prevention programs. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A minimum discrimination information approach for hidden Markovmodeling

An iterative approach for minimum-discrimination-information (MDI) hidden Markov modeling of information sources is proposed. The approach is developed for sources characterized by a given set of partial covariance matrices and for hidden Markov models (HMMs) with Gaussian autoregressive output probability distributions (PDs). The approach aims at estimating the HMM which yields the MDI with respect to all sources that could have produced the given set of partial covariance matrices. Each iteration of the MDI algorithm generates a new HMM as follows. First, a PD for the source is estimated by minimizing the discrimination information measure with respect to the old model over all PDs which satisfy the given set of partial covariance matrices. Then a new model that decreases the discrimination information measure between the estimated PD of the source and the PD of the old model is developed. The problem of estimating the PD of the source is formulated as a standard constrained minimization problem in the Euclidean space. The estimation of a new model given the PD of the source is done by a procedure that generalizes the Baum algorithm. The MDI approach is shown to be a descent algorithm for the discrimination information measure, and its local convergence is proved     

Automatic versus reflective social problem solving in relation to children's sociometric status.

Children's automatic and reflective social problem-solving skills were compared by requiring them to generate solutions to hypothetical social problems immediately after hearing them or after being required to wait 20 sec before answering. When responding immediately, a condition designed to evoke Ss' automatic response tendencies, both aggressive and nonaggressive, rejected boys generated fewer verbal assertion responses and more conflict-escalating responses than did nonrejected boys. When required to delay before responding, a condition that encouraged reflective reasoning, only the responses of aggressive rejected boys differed from those of nonrejected boys. Similar status-related differences in the solutions proposed by female Ss were not found. The implications of these findings for aggressive and rejected children's social problem-solving deficiencies are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Detecting the Presence of Speech Using ADPCM Coding

When speech is coded using a differential pulse-code modulation system with an adaptive quantizer, the digital code words exhibit considerable variation among all quantization levels during both voiced and unvoiced speech intervals. However, because of limits on the range of step sizes, during silent intervals the code words vary only slightly among the smallest quantization steps. Based on this principle, a simple algorithm for locating the beginning and end of a speech utterance has been developed. This algorithm has been tested in computer simulations and has been constructed with standard integrated circuit technology.     

Children's beliefs about familiar and unfamiliar peers in relation to their sociometric status.

Examined children's general beliefs about familiar and unfamiliar peers in relationship to their sociometric status and their experience with parents. In the initial phase involving 886 4th and 5th graders, submissive rejected children but not aggressive rejected children reported less positive beliefs about peers than average status children. In the 2nd portion, which included 77 boys and girls from the larger sample, no relationship between children's sociometric status and their beliefs about unfamiliar peers was found. Beliefs about unfamiliar peers were related, however, to children's perception of the amount of acceptance and support they received from parents. Implications of these findings for children's social competence are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A cross-contextual analysis of boys' social competence: From family to school.

Examined the extent to which the hostile attributions and coercive behaviors of mothers and sons were associated with indices of aggression, acceptance by peers, and teacher-rated social competence in the peer group. Ss were 104 married and divorced mothers and their sons (aged 7–9 yrs). Mothers' and sons' hostile attributions were significantly related to the coerciveness of their interactions, but only mothers' attributions related to reports of the children's aggression in the classroom. Boys who reported many stressful events in their lives behaved coercively with their mothers and were viewed as more aggressive and less socially competent with peers. The relation between stressful life events and the boys' aggression with their peers was mediated, in part, by boys' coerciveness with their mothers. The association between boys' coerciveness with their mothers and social acceptance by peers appeared to be mediated by the aggressiveness of their interactions with their peers. (PsycINFO Database Record (c) 2010 APA, all rights reserved)