Speech Recognition. Wideband Speech Recognition Using Feature Extraction Techniques And Supervised Learning

      Аннотация: Information Technology advancements are happening at a rapid speed and the way people interact with computers are also keeping pace with the technology. Speech recognition is the process of translating an acoustic (a branch of physics that studies sound) signal, captured by a microphone or a telephone, to a set of words for speech understanding. The recognized words can be used as commands and control, data entry, and document preparation. Accurate recognition of speech is one of the most difficult problems in speech recognition technology today. When speech is produced in a carefully planned manner, automatic speech recognition (ASR) systems are very successful at accurate recognition and transcription. In response to casual speech, ASR systems produce more than twice as many errors compared to recognition of the same speech read carefully.

Ключевые слова: Linear Predictive Coding, Mel Frequency Coefficients, Deep Neural Network, Work Error Rate