Automatic Quality Assessment of Speech-Driven Synthesized Gestures

Audio quality issue for automatic speech assessment

Recently, in the language testing field, automatic speech recognition (ASR) technology has been used to automatically score speaking tests. This paper investigates the impact of audio quality on ASR-based automatic speaking assessment. Using the read speech data in the International English Speaking Test (IEST) practice test, we annotated audio quality and compared scores rated by humans, speec...

Quality Evaluation of Synthesized Speech

Automatic speech/non-speech classification using gestures in dialogue

This paper presents an experiment carried out to determine what aspects of motion are associated with speech and what aspects are associated with non-speech in spontaneous dyadic communication. Six dialogs were analysed, and results show that the successful prediction of speech activity from motion differs considerably depending on the characteristics of the dialogue. The classification accurac...

Parametric quality assessment of synthesized textures

In this paper, we present the results of a study designed to investigate the visual factors which contribute to the perceived quality of synthesized textures. A psychophysical experiment was performed in which subjects rated the quality of textures synthesized from a variety of modern texture-synthesis algorithms. The ratings were given in terms of how well each synthesized texture represented ...

Application of automatic speech recognition to quantitative assessment of tracheoesophageal speech with different signal quality.

OBJECTIVE Tracheoesophageal voice is state-of-the-art in voice rehabilitation after laryngectomy. Intelligibility on a telephone is an important evaluation criterion as it is a crucial part of social life. An objective measure of intelligibility when talking on a telephone is desirable in the field of postlaryngectomy speech therapy and its evaluation. PATIENTS AND METHODS Based upon successf...