The rapid development of in-car communication systems in recent years has created problematic human interface challenges. Modern human-computer interfaces are integrated into car's communication systems to make its functionality easily accessible. This paper presents a realistic talking head, which enables a user interface with multi-modality. A talking head in human-car interfaces allows a mor...

Speaker identification systems perform well under the neutral talking condition; however, they suffer sharp degradation under the shouted talking condition. In this paper, the second-order hidden Markov models (HMM2s) have been used to improve the recognition performance of isolated-word text-dependent speaker identification systems under the shouted talking condition. Our results show that HMM...

The Filibuster text-to-speech system is specifically designed and developed for the production of digital talking textbooks at university level for students with print impairments. Currently, the system has one Swedish voice, 'Folke', which has been used in production at the Swedish Library of Talking Books and Braille (TPB) since 2007. In August 2008 the development of a Norwegian voice (bokmå...

In broadcast speech, there are different speaking styles among different TV or radio programs. It is known that news announcing is a very distinctive style; it's quite distinct from others, e.g. talking style. What is the difference between news announcing style and talking style? In this study, we reports our studies on comparison of two speaking styles based on broadcast speech corpus, which ...

We report on the incorporation of a North American aboriginal procedure called "the talking circle" into primary care in areas serving this population. Communication is regulated through the passing of a talking piece (an object of special meaning or symbolism to the circle facilitator, who is usually called the circle keeper). Twelve hundred people participated in talking circles in which 415 ...

In order to render a high quality, versatile 3D talking head, a stable, high frame rate AV data acquisition system is constructed. It can capture 3D position, surface orientation and albedo texture of the talking head video images along with the corresponding speech signals. The system consists of a computer controlled LED lighting subsystem; high speed stereo cameras; a microphone; and a compu...

WHAT IS SLEEP TALKING? Sleep talking (or somniloquy) can be considered as a part of a larger family of types of “sleep utterances,” such as mumbling, laughing, groaning, and whistling during sleep. The ancient Greek philosopher Heraclitus of Ephesus already observed someone sleep talking about 2,500 years ago, so it is not a very recent discovery. It happens at all ages (provided that one is ca...

Speaker identification performance is almost perfect in neutral talking environments. However, the performance is deteriorated significantly in shouted talking environments. This work is devoted to proposing, implementing, and evaluating new models called Second-Order Circular Suprasegmental Hidden Markov Models (CSPHMM2s) to alleviate the deteriorated performance in the shouted talking environ...

This paper addresses the problem of multimedia presentation of a moving and talking head. Existing approaches either use a 3D geometrical representation or multiple 2D views to model and reconstruct faces. To achieve realistic appearance and personalization, and avoid complex models, we propose two approaches. First, we show how pure image-based view morphing can be used to create new moving an...