Music and Speech

This chapter discusses the digital audio—creating or synthesizing sounds using the computer. It gives an introduction to two aspects of audio synthesis, namely generation of music and of speech. Synthesized sounds are a set of instructions to the hardware audio device on how and when to produce sound. The Musical Instrument Digital Interface (MIDI) format is the most widely used digital format for generating synthesized sound. Sampled sounds are used where narration, testimonials, voice-overs, music, and sounds are required. Synthesized sound can be used to create a soothing atmosphere during a presentation or in a multimedia application. Human communication is dominated by speech and hearing. Speech is the most natural form of human communication. Speech is produced by inhaling, expanding the rib cage, and lowering the diaphragm, so that air is drawn into the lungs. The effects of speech are distortion, noise, and clipping. The synthesized speech consists of text-to-speech synthesis and speech-to-text synthesis. The speaker systems, vocabulary, and continuous speech and isolated-word system are also discussed. The chapter also provides a practice exercise.