In corpus-based speech synthesis, the quality of the synthetic speech critically depends on the speech corpus. Since the high vowel in Japanese might be devoiced in the real speech, we should detect and transcribe them automatically in the corpus construction. In this paper, we apply the HMM-based method, and adopt two kinds of likelihood differences as voicing measures for different focuses. T...

A speech signal contains many levels of information. Speech conveys the information about the language being spoken, the emotion, gender, and the identity of the speaker. Features parameters extracted from speech are very useful for speaker recognition as well as speech recognition. In this paper, the features LPC and MFCC are computed of Assamese vowel phonemes which will be helpful to develop...

Speech recognition techniques have been developed dramatically in recent years. Nevertheless, errors caused by environmental noise are still a serious problem in recognition. Employing algorithms to detect and follow the motion of lips have been widely used to improve the performance of speech recognition algorithms. This paper presents a novel technique to recognize vowels. Lip features extrac...

The neural basis of speech recognition and, more generally, sound processing is not well understood. A simple subset of the task of speech recognition, learning to categorise vowel sounds, provides some insights into the more general problems. A simulated neural system that performs this task is described. The system is based on relatively accurate fatiguing leaky integrate and fire neurons, an...