S. R. Mahadeva Prasanna - Böcker

The papers present current research in the area of computer speech processing including audio signal processing, automatic speech recognition, speaker recognition, computational paralinguistics, speech synthesis, sign language and multimodal processing, and speech and language resources.

The two-volume proceedings set LNAI 14338 and 14339 constitutes the refereed proceedings of the 25th International Conference on Speech and Computer, SPECOM 2023, held in Dharwad, India, during November 29–December 2, 2023.The 94 papers included in these proceedings were carefully reviewed and selected from 174 submissions. They focus on all aspects of speech science and technology: ​automatic speech recognition; computational paralinguistics; digital signal processing; speech prosody; natural language processing; child speech processing; speech processing for medicine; industrial speech and language technology; speech technology for under-resourced languages; speech analysis and synthesis; speaker and language identification, verification and diarization.

The two-volume proceedings set LNAI 14338 and 14339 constitutes the refereed proceedings of the 25th International Conference on Speech and Computer, SPECOM 2023, held in Dharwad, India, during November 29–December 2, 2023.The 94 papers included in these proceedings were carefully reviewed and selected from 174 submissions. They focus on all aspects of speech science and technology: ​automatic speech recognition; computational paralinguistics; digital signal processing; speech prosody; natural language processing; child speech processing; speech processing for medicine; industrial speech and language technology; speech technology for under-resourced languages; speech analysis and synthesis; speaker and language identification, verification and diarization.

The present volume is a compilation of research work in computation, communication, vision sciences, device design, fabrication, upcoming materials and related process design, etc. It is derived out of selected manuscripts submitted to the 2014 National Workshop on Advances in Communication and Computing (WACC 2014), Assam Engineering College, Guwahati, Assam, India which is emerging out to be a premier platform for discussion and dissemination of knowhow in this part of the world. The papers included in the volume are indicative of the recent thrust in computation, communications and emerging technologies. Certain recent advances in ZnO nanostructures for alternate energy generation provide emerging insights into an area that has promises for the energy sector including conservation and green technology. Similarly, scholarly contributions have focused on malware detection and related issues. Several contributions have focused on biomedical aspects including contributions related to cancer detection using active learning, application of clinical information in MECG using sample and channel convolution matrices for better diagnostic decision, etc. Some other works have focused on the DCT-domain linear regression of ECG signals, SVD Analysis on reduced 3-lead ECG data, the quantification of diagnostic information on ECG signal, a compressed sensing approach with application in MRI, learning aided image de-noising for medical applications, etc. Some works have dealt with application of audio fingerprinting for multi-lingual Indian song retrieval, semi-automatic approach to segmentation and the marking of pitch contours for prosodic analysis, semiautomatic syllable labeling for Assamese language, stressed speech recognition, handwriting recognition in Assamese script, speaker verification considering the effect of session variability and the block matching for motion estimation, etc. The primary objective of the present volume is to prepare a document for dissemination of and discussion on emerging areas of research in computation and communication as aimed by WACC 2014. We hope that the volume will serve as a reference book for researchers in these areas.