Sebastian Möller

Assessment and prediction of speech quality in telecommunications

Definitions and Abbreviations. Acknowledgements. Summary. 1. Introduction. 2. Considerations on Quality. 3. Factors Influencing the Quality of Service. 4. Quality Assessment in Telecommunications. 5. Models For Predicting Speech Comm. Quality and Service-Related Models. 6. Relations between Factors Governing the Quality of Service. 7. Quality of Prediction Models. 8. Final Discussion and Conclusions. Appendices. Bibliography. Index.

T-V-model: Parameter-based prediction of IPTV quality

The paper presents a parameter-based model for predicting the perceived quality of transmitted video for IPTV applications. The core model we derived can be applied both to service monitoring and network or service planning. In its current form, the model covers H.264 and MPEG-2 coded video (standard and high definition) transmitted over IP-links. The model includes factors like the coding bit-rate, the packet loss percentage and the type of packet loss handling used by the codec. The paper provides an overview of the model, of its integration into a multimedia model predicting audio-visual quality, and of its application to service monitoring. A performance analysis is presented showing a high correlation with the results of different subjective video quality perception tests. An outlook highlights future model extensions.

Evaluating spoken dialogue systems according to de-facto standards: A case study

In the present paper, we investigate the validity and reliability of de-facto evaluation standards, defined for measuring or predicting the quality of the interaction with spoken dialogue systems. Two experiments have been carried out with a dialogue system for controlling domestic devices. During these experiments, subjective judgments of quality have been collected by two questionnaire methods (ITU-T Rec. P.851 and SASSI), and parameters describing the interaction have been logged and annotated. Both metrics served the derivation of prediction models according to the PARADISE approach. Although the limited database allows only tentative conclusions to be drawn, the results suggest that both questionnaire methods provide valid measurements of a large number of different quality aspects; most of the perceptive dimensions underlying the subjective judgments can also be measured with a high reliability. The extracted parameters mainly describe quality aspects which are directly linked to the system, environmental and task characteristics. Used as an input to prediction models, the parameters provide helpful information for system design and optimization, but not general predictions of system usability and acceptability.

Predicting the quality and usability of spoken dialogue services

In this paper, we compare different approaches for predicting the quality and usability of spoken dialogue systems. The respective models provide estimations of user judgments on perceived quality, based on parameters which can be extracted from interaction logs. Different types of input parameters and different modeling algorithms have been compared using three spoken dialogue databases obtained with two different systems. The results show that both linear regression models and classification trees are able to cover around 50% of the variance in the training data, and neural networks even more. When applied to independent test data, in particular to data obtained with different systems and/or user groups, the prediction accuracy decreases significantly. The underlying reasons for the limited predictive power are discussed. It is shown that - although an accurate prediction of individual ratings is not yet possible with such models - they may still be used for taking decisions on component optimization, and are thus helpful tools for the system developer.

Analysis of infant cries for the early detection of hearing impairment

Abstract The basic hypothesis is that cry vocalizations of hearing-impaired infants differ from those of their counterparts with normal hearing abilities due to the lack of auditory feedback. This assumption, based on observations made by clinical experts, is investigated by means of auditory experiments with naive and expert listeners, and by signal analysis of the cries. The listening experiment shows that it is possible for experts to auditorily classify cries for both infant groups, based on the voice related and melodic cry features. The cries of profoundly hearing-impaired infants are different regarding their perceived sound, rhythm and melody. The sound may well be correlated to spectral characteristics, and melodic and rhythmic parameters are extracted which differ significantly for the two infant groups. The findings are discussed in the context of a cry production model. The extracted signal parameters enable an automatic classification of the cries by means of topological feature maps, which may later be used as the basis for an early supplementary diagnostic tool.

Neuronal networks and self-organizing maps: new computer techniques in the acoustic evaluation of the infant cry

Neuronal networks are computer-based techniques for the evaluation and control of complex information systems and processes. So far, they have been used in engineering, telecommunications, artificial speech and speech recognition. A new approach in neuronal network is the self-organizing map (Kohonen map). In the phase of learning, the map adapts to the patterns of the primary signals. If, the phase of using the map, the input signal hits the field of the primary signals, it resembles them and is called a winner. In our study, we recorded the cries of newborns and young infants using digital audio tape (DAT) and a high quality microphone. The cries were elicited by tactile stimuli wearing headphones. In 27 cases, delayed auditory feedback was presented to the children using a headphone and an additional three-head tape-recorder. Spectrographic characteristics of the cries were classified by 20-step bark spectra and then applied to the neuronal networks. It was possible to recognize similarities of different cries of the same children as well as interindividual differences, which are also audible to experienced listeners. Differences were obvious in profound hearing loss. We know much about the cries of both healthy and sick infants, but a reliable investigation regimen, which can be used for clinical routine purposes, has yet not been developed. If, in the future, it becomes possible to classify spectrographic characteristics automatically, even if they are not audible, neuronal networks may be helpful in the early diagnosis of infant diseases.

Speech Quality While Roaming in Next Generation Networks

In NGNs, handovers between different wireless access technologies provide seamless roaming during voice calls. The resulting speech quality depends on the audio bandwidth of the speech codecs used in the respective networks, as well as on degradations resulting from the handover, coding, and packet loss. We present the results of four listening experiments where speech quality is quantified as a function of network and codec characteristics, and compare them to estimations obtained from instrumental models. The results show when and under which circumstances a network handover and/or codec changeover should be scheduled in order to obtain better speech quality. This is important for the development of high-quality roaming strategies.

A new Taxonomy for the Quality of Telephone Services Based on Spoken Dialogue Systems

This document proposes a new taxonomy for describing the quality of services which are based on spoken dialogue systems (SDSs), and operated via a telephone interface. It is used to classify instrumentally or expert-derived dialogue and system measures, as well as quality features perceived by the user of the service. A comparison is drawn to the quality of human-to-human telephone services, and implications for the development of evaluation frameworks such as PARADISE are discussed.

Quality Dimensions of Narrowband and Wideband Speech Transmission

The study presented in this paper aims at exploring the perceptual spaces evoked for users of two different telephone scenarios: traditional narrowband speech transmission, and mixed narrowband/wideband speech transmission that may be encountered in todays Voice-over-IP services. Underlying dimensions that constitute the skeleton of these spaces are revealed by auditory experiments, following two different paradigms of judgment: a) Similarity-scaling, and b) Attribute-scaling (Semantic Differential) with subsequent a) Multidimensional Scaling, and b) Principal Component Analysis of a diverse set of stimuli. Similar configurations are obtained which are unequivocally interpretable. Three common dimensions, valid for both the narrowband and the wideband scenario can be identified: Discontinuity, Noisiness, and Coloration. In addition, the wideband space is extended by a further, wideband-specific dimension. Integral listening-quality can well be modeled by means of these dimensions. In both scenarios, Discontinuity represents the most important quality feature. The presented work forms the basis for instrumental diagnostic quality measures.

Evaluating the speech output component of a smart-home system

This paper describes four experiments which have been carried out to evaluate the speech output component of the INSPIRE spoken dialogue system, providing speech control for di.erent devices located in a x91x91smartx92x92 home environment. The aim is to quantify the impact of different factors on the quality of the system, when addressed either in the home or from a remote location (office, car). Factors analyzed in the experiments include the characteristics of the machine agent during the interaction (voice, personality), the physical characteristics of the usage environment (acoustic user interface, background noise, electrical transmission path), as well as task-related characteristics (listening-only vs. interaction situation, parallel tasks). The results show a significant impact of agent and environmental factors, but not of task factors. Potential reasons for this .nding are discussed. They serve as a basis for design decisions which have been taken for the final system.