This paper presents a new definition of service delivery platform based on recent industry standard activities at OMA (open mobile alliance): the OSE (OMA service environment). The proposed blueprint is consistent with NGN (next generation networks) as well as legacy networks. The SDP blueprint discussed in this paper follows SOA (service oriented architecture) principles and basic IT technologies and principles. It clarifies many aspects misunderstood or confused in the telco industry like: How to develop faster and at lower cost competitive telco services; What is SOA for telcos; How do Parlay and IMS relate; How to characterize or implement the IMS service layer; How do IMS, Vanilla SIP and other SIP service deployment relate; What is SCIM and how to implement it; How to accommodate legacy, new and future network technologies; how to achieve true convergence across multiple networks; How to support third party content and service providers, etc. The paper also discusses options to realize a SDP. In particular, it analyzes J2EE readiness for telco deployments, discusses SDP implemented as J2EE realization of OSE. The paper concludes with a recommendation to base SDPs on J2EE middleware and provides some prediction of the evolution of the platform to provide mobile, voice and communications capabilities to enterprises as well as telcos.

We present a transformation-based, multigrained data modeling technique in the context of text independent speaker recognition, aimed at mitigating difficulties caused by sparse training and test data. Both identification and verification are addressed, where we view the entire population as divided into the target population and its complement, which we refer to as the background population. First, we present our development of maximum likelihood transformation based recognition with diagonally constrained Gaussian mixture models and show its robustness to data scarcity with results on identification. Then for each target and background speaker, a multigrained model is constructed using the transformation based extension as a building block. The training data is labeled with an HMM based phone labeler. We then make use of a graduated phone class structure to train the speaker model at various levels of detail. This structure is a tree with the root node containing all the phones. Subsequent levels partition the phones into increasingly finer grained linguistic classes. This method affords the use of fine detail where possible, i.e., as reflected in the amount of training data distributed to each tree node. We demonstrate the effectiveness of the modeling with verification experiments in matched and mismatched conditions.

Presents results on speaker identification with a population size of over 10000 speakers. Speaker modeling is accomplished via our transformation enhanced multigrained models. Pursuing two goals, the first is to study the performance of a number of different systems within the modeling framework of multi-grained models. The second is to analyze performance as a function of population size. We show that the most complex models within the framework perform the best and demonstrate that, in approximation, the identification error rate scales linearly with the log of the population size for the described system. Further, we develop a candidate rejection technique based on our analysis of the system performance which indicates a low confidence in the identity chosen.

User interface is a mean to an end —its primary goal is to capture user intent and communicate the results of the re-quested computation. On today’s devices, user interaction can be achieved through a multiplicity of interaction modal-ities including speech and visual interfaces. As we evolve toward an increasingly connected world where we access and interact with applications throughmul-tiple devices, it becomes crucial that the various access paths to the underlying content be synchronized. This synchro-nization ensures that the user interacts with the same un-derlying content independent of the interaction modality — despite the difference in presentation that eachmodalitymight impose. It also ensures that the effect of user interaction in any given modality is reflected consistently across all avail-able modalities. We describe an application framework that enables tightly synchronized multimodal user interaction. This framework derives its power from representing the application model in a modality-independent manner, and by traversing this model to produce the various synchronizedmultimodal views. As the user interaction proceeds, we maintain our current position in the model and update the application data as de-termined by user intent, then reflect these updates in the var-ious views being presented. We conclude the paper by outlining an example that demonstrates this tightly synchronized multimodal interac-tion, and describe some of the future challenges in building such multimodal frameworks. 1.

This paper describes an implementation of the concept of conversational speech biometrics approach to personal authentication in the telephony environment. An application-independent module including a natural language-enabled part for verbal verification and identification and an acoustic speaker recognition engine for voice-print analysis are combined using a special verification/identification protocol which allows the application to adapt the session according to the dialog development and the query/command security. The results validate the feasibility and advantages of the concept of integrating the speaker and speech recognition technology. Users familiar with the system can log into the system with 2.7% or 3.2% false rejection and ca. 3/spl times/10/sup -11/% or 10/sup -6/% false acceptance rates in about 40 sec or 20 sec respectively. This makes speaker recognition for the first time deployable for high security applications even with today's technology-a claim that can't be made with other speaker recognition technology. The system has a client-server architecture and is suitable for various applications and platforms.

We describe our formulation of transformation enhanced data modeling used to develop a multi-grained data analysis approach to text independent speaker recognition. The broad goal is to address difficulties caused by sparse training and test data. First, our development of maximum likelihood transformation based recognition with diagonally constrained Gaussian mixture models is detailed. We give results to show its robustness to decreasing training data. Then using the these models as building blocks, a multigrained model structure is developed. For this, the training data must be labeled, e.g. with an HMM based phone labeler. A graduated phone class structure is then used to train the speaker model at various levels of detail. This structure is a tree with the root node containing all the phones. Subsequent levels partition the phones into increasingly finer grained linguistic classes. We demonstrate the effectiveness of the modeling with identification and verification experiments. 1.

CORRECTIVE TRAINING FOR SPEAKER ADAPTATIONXiuyang Yu and Wayne WardCenter for Spoken Language UnderstandingUniversity of Colorado, Boulder, ColoradoABSTRACTThis paper reports results on an experiment to use correctivetraining techniques for rapid acoustic speaker adaptation in asemi-continuous speech recognition system. Decoder outputis used to adjust HMM acoustic models to improvediscrimination between correct words and near misses.Twenty sentences are used as an adaptation set. A speechrecognizer is run on each utterance to generate a wordlattice. The lattice is pruned relative to the correct path. Theforward-backward algorithm is used to align each path in thelattice against the speech input and compute observationcounts. For each input frame, counts in correct models areadjusted upward, and counts in incorrect models are adjusteddownward. The adjusted counts are normalized to generatenew observation probabilities for the models. Theparameters being adjusted are the mixture weights for thesemi-continuous HMMs. The technique reduced word errorfor a test subject by 37% relative.INTRODUCTIONSpeech recognition systems based on Hidden MarkovModels typically experience significant performancedegradation when a speaker is not represented well in thedata that the system was trained on. Rapid speakeradaptation techniques can be very effective in improvingperformance for a novel speaker. These techniques use asmall number of sentences (20-40), whose transcript isknown, to quickly adapt HMM acoustic models to a newspeaker. Such techniques are important, since in order forlonger term adaptation to be able to work, the system mustfunction well enough for the user to be productive. Thesetechniques attempt to correct very poor models quickly toget the system to a usable point for the user. This paperreports results on an experiment to use corrective trainingtechniques to rapidly adapt HMM acoustic models to apoorly recognized speaker.CORRECTIVE TRAININGCorrective training was introduced for speaker-dependentisolated word recognition by [1] and extended to speaker-independent continuous speech recognition by [2]. HiddenMarkov Models are normally trained according to amaximum likelihood criterion; parameters are adjusted tomaximize the probability of the training set. This processdoes not directly minimize the word errors, it does thisindirectly by attempting to assign a high probability to thecorrect utterance. It makes no representation of whatprobability is assigned to near misses. Corrective trainingseeks to directly minimize the number of word errors byadjusting parameters so as to improve discriminationbetween correct words and near misses. The general processis:1. Generate a set of near misses, words which areconfusable with the correct words.2. Align the correct words against the input.3. Align a near miss against the input.4. Modify model such that correct words are more likelyand incorrect ones less likely.5. Repeat steps 2-3 for other near misses.Speech recognizers are used to generate the near misses. In[1] and [2], a sp eech recognizer was used to generate an n-best list for an isolated word or sentence. This list was usedas the set of near misses. Both the correct utterance and nearmiss are aligned against the input. Model parameters arethen adjusted to make the correct words more likely and theincorrect ones less likely.SPHINX-II OBSERVATION ESTIMATESIn order to describe how corrective training is used to adaptour model, it is first necessary to describe the basic model.Our experimental system uses the Carnegie MellonUniversity Sphinx-II system for speech recognition[3],[4],[5]. Sphinx-II uses semi-continuous Hidden MarkovModels [3] to model context dependent phones. Likecontinuous HMM systems, semi-continuous systems use aweighted sum of points on Gaussian Probability DensityFunctions to estimate observation probabilities. Thedifference is that, while continuous systems estimate a set ofdistributions for each HMM state in the system, semi-

This paper presents a distance measure for evaluating the closeness of two sets of distributions. The job of finding the distance between two distributions has been addressed with many solutions present in the literature. To cluster speakers using the pre-computed models of their speech, a need arises for computing a distance between these models which are normally built of a collection of distributions such as Gaussians (e.g., comparison between two HMM models). The definition of this distance measure creates many possibilities for speaker verification, speaker adaptation, speaker segmentation and many other related applications. A distance measure is presented for evaluating the closeness of a collection of distributions with centralized atoms such as Gaussians (but not limited to Gaussians). Several applications including some in speaker recognition with some results are presented using this distance measure.

This paper describes some of the main problems and issues specific to the transcription of broadcast news and describes some of the methods for solving them that have been incorporated into the IBM Large Vocabulary Continuous Speech Recognition System.