Voice and Speech Systems

About Us

Goal of Voice and Speech Systems (VSS) is to conduct Basic Research in the area of Speech Signal Processing and apply it for Product Development in the area of Speech and Hearing. VSS is supported by an enthusiastic team of programmers and researchers. In house experience coupled with cooperation from renowned researchers and institutions is the basis for high quality research and products of VSS.

Research and product development at VSS have been supported by revenue generated from sales. VSS thanks its customers for their support and patronage.

Products

Products developed by VSS have been received well by the speech and hearing professionals and educational institutions. These products have been used by educational institutions for routine clinical training, for Master level dissertations. doctoral theses works and projects sponsored by DOE, Ministry of Health etc. Our product called Vaghmi was nominated for Govt of India President's Award. Products of VSS have been mentioned in a joint parliamentary report. Products Vaghmi and SSL have been recognized by the Rehabilitation Council of India (RCI).

VSS has developed diagnostic and therapeutic software package,Vaghmi. Diagnostic software can be used for acoustic analysis to study voice disorders. This has been installed in major hospitals, private clinics. Voice and Articulation therapy modules are developed with a focus to help hearing impaired. A large number of schools for hearing impaired and spastics have effectively used Vaghmi. It has also been used by musicologists and voice specialists. Disfluency module is used for stuttering patients.

VSS has introduced Vagmi-Rental which is same as Vaghmi software but available on a rental basis. For therapy, clients have to commute a long distance spending considerable time. Also, parent(s) may have to accompany a child to the clinic for therapy. Nowadays most clients have a PC at home. Vagmi-Therapy Home Edition has been introduced for the benefit of clients. They can practice therapy at home. Vagmi-Therapy Home Edition is issued after training through a speech and hearing professional or voice professional or a special teacher of the hearing impaired.

VSS has developed an advanced software tool called Speech Science Lab, SSL, for Speech Signal Analysis and Synthesis that can be used by linguists, phoneticians, engineers etc. SSL can be used for teaching an experimental course in acoustic-phonetics. SSL has been used for several dissertations and doctoral theses. SSL has also been used as a spectral analysis tool in allied areas such as automobile industry, in the analysis of animal sounds etc.

AudioLab is an advanced software tool for diagnosis of central auditory disorders and for testing of dyslexics.

Research Expertise

VSS has been conducting basic research in challenging areas such as articulatory analysis-synthesis, natural sounding synthesis models for text-to-speech systems, speaker and language independent speech recognition based on invariant cues, property detectors etc., segmentation and labeling, variable rate coding, formant tracking etc. It has achieved some degree of success. Some of notable results are robust voiced/unvoiced/silence decision; robust F0 estimation; mapping of tongue contour for vowel therapy; s Vs sh and s Vs z discrimination for frication therapy; natural sounding synthesis for prolongation used in stuttering therapy; segmentation and labeling; synthesis models; articulatory-analysis, synthesis, formant tracking etc.

Many of the research results have been incorporated in to the existing software products.

History

VSS was started by Dr. T. V. Ananthapadmanabha is a researcher cum entrepreneur. He holds a PhD degree in electrical communication engineering and a recipient of Gold Medal from the Indian Institute of Science and Sir C V Raman Award from ASI. He has worked in world renowned labs such as Royal Institute of Technology, Stockholm; Carnegie-Mellon University, Pittsburgh; AT&T Bell Labs, Murray Hill, NJ; MIT, Cambridge.

Initially VSS started with a consultancy project on LPC-10 coding for Ericssons, Sweden during 1985. Then it developed token announcement system and transferred the know-how to a private manufacturer. For research purposes, Ananthapadmanabha developed a large number of speech analysis and synthesis programs on main frame computers. These programs were ported to PC platform. These programs were modified for diagnostics and therapeutic purposes. The DOS version software packages on PC were introduced in Indian market during 1990. The products became popular amongst the professionals and educational institutions in the field. VSS had to keep pace with the rapid changes in PC technology and operating systems. Window version of software packages have been introduced into market.

Ananthapadmanabha has been actively involved in research. He has published a number of papers and reports. He has conducted a number of workshops to create awareness amongst the professionals in the field. He has guided many MS and Doctoral dissertations. He lectures to students on advanced topics.

Address:
Voice and Speech Systems, No. 53(old), 127 (new), "Girinivas", Temple Road, 13th Cross, Malleswaram, Bangalore 560 003, India
Tel: 080-23312113, 080-41490207 Cell: (0)98868 63651
Email: tva_vss@yahoo.com , vagmi_vss@yahoo.com