Dmitry Sityaev

Learn More
Evaluation of TTS systems is essential to assess performance. The ITU-T P.85 standard was introduced in 1994 to assess the overall quality of speech synthesis systems. However it has not been widely accepted or used. This paper compares the ITU test to more commonly used tests for intelligibility (semantically unpredictable sentences (SUS)) and naturalness(More)
This paper addresses the modelling in text-to-speech of the rising intonation pattern in American English which is often found in yes-no questions. A small corpus containing yes-no questions was recorded and analysed. F0 was then modelled using an automatic procedure. The paper also reports on the stability of alignment of F0 targets in rising intonation(More)
This paper describes two approaches to assigning prosodic phrase structure and pauses to text and investigates the impact of errors in the assignments for different granularities of prosodic phrase structure. One approach uses a cascaded combination of models trained separately for prediction of prosodic phrase structure and pauses and the other uses a(More)
This paper describes a novel solution which allows to quickly build and develop multi-channel applications. Due to the popularity of a smartphone, a new paradigm of applications called Visual IVR has been emerging recently, where visual navigation replaces the traditional DTMF or voice-enabled dialogue control. The described solution brings a unified(More)
This paper presents empirical results of the corpus-based study on the relationship between accentuation and referent information status. It was found that there is no one-to-one relationship between “new” vs. “given” information and presence vs. absence of accent. Contrary to the widely spread claim that “given” items appear to be deaccented, the results(More)
Intelligibility assessment is one of the important aspects in the text-to-speech system (TTS) evaluation. Several intelligibility assessment methods have been proposed and successfully applied to European languages, both at word level and sentence level. Since Mandarin has its own unique features, these methods must be modified when applying to Mandarin.(More)
This paper describes a new platform called Lexee developed as part of a cloud-based Angel offering which allows to rapidly develop voice-enabled mobile applications. The solution allows to rapidly build application flows without any significant investments into software or extensive knowledge of programming. The Lexee SDK described in this paper gives(More)
  • 1