John L. Arnott

Toward the simulation of emotion in synthetic speech: A review of the literature on human vocal emotion

There has been considerable research into perceptible correlates of emotional state, but a very limited amount of the literature examines the acoustic correlates and other relevant aspects of emotion effects in human speech; in addition, the vocal emotion literature is almost totally separate from the main body of speech analysis literature. A discussion of the literature describing human vocal emotion, and its principal findings, are presented. The voice parameters affected by emotion are found to be of three main types: voice quality, utterance timing, and utterance pitch contour. These parameters are described both in general and in detail for a range of specific emotions. Current speech synthesizer technology is such that many of the parameters of human speech affected by emotion could be manipulated systematically in synthetic speech to produce a simulation of vocal emotion; application of the literature to construction of a system capable of producing synthetic speech with emotion is discussed.

Implementation and testing of a system for producing emotion-by-rule in synthetic speech

Abstract A system is described which adds simulated emotion effects to synthetic speech. The control parameters of a speech synthesizer are controlled by rule in order to simulate the features of emotion expressed in the human voice. The system can simulate six vocal emotions and was evaluated with naive listeners. The results indicated that the system was producing recognizable vocal emotions, with perception rankings similar to those found by previous research on human emotional speech. This system has been developed for use in voice prosthesis systems for non-vocal disabled persons, although it could be used to enhance any application which uses rule-based synthetic speech.

Using spatial cues to improve videoconferencing

A conventional approach to multiparty videoeonferencing is to support a four way meeting using a Picture-in-aPicture (PIP) device, In this approach, each remote participant’s image is placed in one quadrant of the screen of a single monitor. This common view is then distributed to each person. In addition, the audio from eaeh participant is combined, and all voices emanate from a single loudspeaker.

Methods for human - computer interaction research with older people

Experimental research in human – computer interaction commonly uses participant groups that are unrepresentative of demographic realities, being young, technically knowledgeable and highly educated. One way of reflecting society more accurately in research is to include older adults in research groups, but the elicitation of high-quality data from these participants requires alterations in research methods and organization. In the present paper, methodological and organizational experiences from a range of research studies with older participants are reported. It concludes with a list of guidelines for maximizing the research outcomes of working with older adults.

Adaptive and predictive techniques in a communication prosthesis

This paper describes a communication aid and keyboard emulator which has been developed at Dundee University. The device, Predictive Adaptive Lexicon (PAL), exploits the redundancy in natural language to reduce the key pushes or character selections necessary during the composition of text. Word predictions are offered to the user from a dictionary, and if one of these is selected the word is completed by PAL. PAL adapts to the users vocabulary by automatically capturing words which are not already in the dictionary. These will thereafter be offered in prediction lists. A reduction in the number of character inputs necessary to enter any given text of over 50% is possible when using PAL, giving the user a considerable saving in time and effort.

Probabilistic character disambiguation for reduced keyboards using small text samples

Reduced keyboards are text typing keyboards which contain fewer than 26 alphabetic keys, and which may therefore be accessed and used by certain physically disabled persons more easily than a conventional “QWERTY” typing keyboard. Automatic character disambiguation systems enable text to be typed upon a reduced keyboard with a keying efficiency approaching one key/character, despite the fact that each key represents more than one alphabetic character. Existing disambiguation systems typically use probabilistic models of character sequences (n-grams) from representative text samples to predict the next character, and hence disambiguate among the different characters on each key. N-grams for such disambiguation models have been extracted previously from large (1 million word) text corpora. The research reported here shows that a much smaller corpus of limited domain can be used with similar results, thus facilitating development of disambiguation systems by eliminating the need for a large corpus. Four redu...

Methodologies for involving older adults in the design process

Older people provide much greater challenges to user-centred design than more traditional user groups. It is also very important to encourage (often young) designers to develop a relationship with, and an empathy for, older users. It is recommended that older users be fully integrated into the design process. Researchers, however, need to take care to be sensitive to the characteristics, sensory and cognitive capabilities, and the attitudes of older people to computers and to being included in research studies. The paper suggests strategies for doing this, together with the more radical approach of using professional actors as surrogates for real older users.

Emotional stress in synthetic speech: progress and future directions

Abstract Current text-to-speech systems have very good intelligibility, but most are still easily identified as artificial voices and no commercial system incorporates prosodic variation resulting from emotion and related factors. This is largely due to the complexity of identifying and categorising the emotion factors in natural human speech, and implementing these factors within synthetic speech. However, prosodic content in synthetic speech is seen as increasingly important, and there is presently renewed interest in the investigation of human vocal emotion and the expansion of synthesis models to allow greater prosodic variation. Such models could also be used as practical tools in the investigation and validation of models of emotion and other speech-altering Stressors. This paper reviews progress to date in the investigation of human vocal emotions and their simulation in synthetic speech, and requirements for future research which is required to develop this area are also presented.

Studies of turn-taking in computermediated communications

Groupware is designed to provide opportunities for physically dispersed computer users to co-operate in a manner akin to a face-to-face meeting. Little is understood, however, of the factors that might influence its success. One possible factor is ‘floor control’, or turntaking, which is an important feature of face-to-face meetings. The paper describes experiments designed to examine the importance of turn-taking in computer-mediated communications, in comparison with face-to-face conversations, and considers means whereby turntaking behaviour, and hence the effectiveness of groupware, can be improved.

Applying an analysis of acted vocal emotions to improve the simulation of synthetic speech

All speech produced by humans includes information about the speaker, including conveying the emotional state of the speaker. It is thus desirable to include vocal affect in any synthetic speech where improving the naturalness of the speech produced is important. However, the speech factors which convey affect are poorly understood, and their implementation in synthetic speech systems is not yet commonplace. A prototype system for the production of emotional synthetic speech using a commercial formant synthesiser was developed based on vocal emotion descriptions given in the literature. This paper describes work to improve and augment this system, based on a detailed investigation of emotive material spoken by two actors (one amateur, one professional). The results of this analysis are summarised, and were used to enhance the existing emotion rules used in the speech synthesis system. The enhanced system was evaluated by naive listeners in a perception experiment, and the simulated emotions were found to be more realistic than in the original version of the system.