Asoke Kumar Datta – författare

This book presents the consolidated acoustic data for all phones in Standard Colloquial Bengali (SCB), commonly known as Bangla, a Bengali language used by 350 million people in India, Bangladesh, and the Bengali diaspora. The book analyzes the real speech of selected native speakers of the Bangla dialect to ensure that a proper acoustical database is available for the development of speech technologies. The acoustic data presented consists of averages and their normal spread, represented by the standard deviations of necessary acoustic parameters including e.g. formant information for multiple native speakers of both sexes.

The study employs two important speech technologies:(1) text to speech synthesis (TTS) and (2) automatic speech recognition (ASR). The procedures, particularly those related to the use of technologies, are described in sufficient detail to enable researchers to use them to create technical acoustic databases for any other Indian dialect. The book offers aunique resource for scientists and industrial practitioners who are interested in the acoustic analysis and processing of Indian dialects to develop similar dialect databases of their own.

This book presents details of a text-to-speech synthesis procedure using epoch synchronous overlap add (ESOLA), and provides a solution for development of a text-to-speech system using minimum data resources compared to existing solutions. It also examines most natural speech signals including random perturbation in synthesis. The book is intended for students, researchers and industrial practitioners in the field of text-to-speech synthesis. 

The book presents the history of time-domain representation and the extent of its development along with that of spectral domain representation in the cognitive and technology domains. It discusses all the cognitive experiments related to this development, along with details of technological developments related to both automatic speech recognition (ASR) and text to speech synthesis (TTS), and introduces a viable time-domain representation for both objective and subjective analysis, as an alternative to the well-known spectral representation.

The book also includes a new cohort study on the use of lexical knowledge in ASR.

This book addresses the acoustic signal analysis and spectral dynamics of the tanpura, an Indian plucked string instrument. In addition, it strives to provide a logical and objective explanation of Indian classical musicians’ cognitive experience. Issues of relevance in this regard include the rich, mellifluous sound; the undulation of the loudness; the somewhat cyclical variation of the timbre, which is strongly related to these undulations; and the occasional perception of virtual notes to which no strings are tuned.

The book analyses the materials used in the tanpura, the instrument’s simple structure, the intricacies of the lower bridge, and the theory of string vibration with variable string length. Cognitive experiments to provide the basis for perceptual quality assessment, as well as a methodology for ranking, are described. This is followed by acoustic analyses, both temporal and spectral, for sounds produced by male and female tanpuras, for each individual string and the combined one. An important aspect related to the naturalness of perceived sound, namely the intrinsically associated random perturbations, is also discussed. The apparent irregularities perceived in the acoustic signal produced by the tanpura reveal the importance of examining the signal from the perspective of non-linear analysis, an aspect that is also covered in the book.

Given its scope, the book will appeal to students and researchers in the fields of music acoustics, artificial intelligence, and cognitive science, as well as musicians and musicologists around the world.