International Business Machines Corporation

Marco De Gregorio

Gianluca Gargaro

Stefania Errore

Agostino Colussi

Salvatore Matrone

An approach for enhancing speech reproduction based on recognizing text segments from sound segments of an audio signal. Enhanced text segments are generated from any text segments whose quality indicators do not reach a threshold level, and enhanced speech segments are synthetized from the enhanced text segments. An enhanced sound is reproduced comprising enhanced sound segments based on the enhanced speech segments.

Enhanced reproduction of speech on a computing system

A solution is proposed for monitoring quality of a conference call. Corresponding methods are implemented on a client computing machine of a participant to the conference call, a server computing machine for managing the conference call and a computing system comprising the server computing machine and a plurality of client computing machines, respectively. One or more test signals (having corresponding test frequencies within a human audible range) are generated by each client computing machine in the mute mode without audible effects on the participant. The test signals are transmitted from the client computing machine to the server computing machine. The server computing machine verifies the quality of the conference call for the participant according to a comparison of one or more received signals (received from the client computing machine) with the test signals. Computer programs and computer program products for performing the corresponding methods are also proposed.

Growing community of inventors

Rome, Italy

Marco De Gregorio