In this paper, we have analyzed the impact of confusions on the robustness of phoneme recognitions system. The confusions are detected at the pronunciation and the confusions matrices of the phoneme recognizer. The confusions show that some similarities between phonemes at the pronunciation affect significantly the recognition rates. This paper proposes to understand those confusions in order t...

This paper presents improved HMM/SVM methods for a twostage phoneme segmentation framework, which tries to imitate the human phoneme segmentation process. The first stage performs hidden Markov model (HMM) forced alignment according to the minimum boundary error (MBE) criterion. The objective is to align a phoneme sequence of a speech utterance with its acoustic signal counterpart based on MBE-...

Out-of-vocabulary (OOV) words are the most challenging problem in automatic speech recognition (ASR), especially for morphologically rich languages. Most end-to-end systems performed at word and character levels of a language. Amharic is poorly resourced but This paper proposes hybrid connectionist temporal classification with attention architecture syllabification algorithm system (AASR) using...

In this paper we propose the use of phoneme graphs for word spotting tasks. The proposed phoneme graphs are built using phonetic probabilities estimated at frame level. We also propose an error model on phoneme graphs which allows to simplify the exploration algorithms used for finding phonetic sequences. A phoneme duration model is also applied for avoiding the detection of too short phonetic ...

This paper describes the acoustic characteristics of Bangla consonants, obtained by analyzing the recordings of male and female voices. First, the duration of each phoneme was identified by averaging both the male and female voice data; then, formant were measured and formant comparison was made for controversial phonemes, which also served to resolve the controversies in the existing phoneme i...

Speech synthesis by unit selection requires the segmentation of a large single speaker high quality recording. Automatic speech recognition techniques, e.g. Hidden Markov Models (HMM), can be optimised for maximum segmentation accuracy. This paper presents the results of tuning such a phoneme segmentation system. Firstly, using no text transcription, the design of an HMM phoneme recogniser is o...