In this paper we develop hidden Markov model (HMM) based approaches to identify Chinese dialects spoken in Taiwan. This task can be aided by exploiting various characteristic features of Chinese spoken languages. The baseline system performs phonotactic analysis after the speech utterance is tokenized into a sequence of five broad phonetic classes. The sequential statistics of the resulting sym...

The so called Phone Log-Likelihood Ratio (PLLR) features, computed on phone posterior probabilities provided by phonetic decoders, convey acoustic-phonetic information in a sequence of frame-level vectors. Thus, PLLRs can be easily plugged into traditional acoustic systems just by replacing MFCCs, PLPs or whatever other representation. PLLR features were used under an iVector-PLDA approach in o...

In this paper, the acoustic–phonetic characteristics of American English stop consonants are investigated. Features studied in the literature are evaluated for their information content and new features are proposed. A statistically guided, knowledge-based, acoustic–phonetic system for the automatic classification of stops, in speaker independent continuous speech, is proposed. The system uses ...

In this paper, we present investigations on using segmental phonetic features in an N-best solutions post processing of an HMM based ASR system. These phonetic features are extracted by means of neural-fuzzy networks. Specialized neural-fuzzy networks are defined to recognize specific phonetic features (consonant/vowel, voiced/unvoiced, ...). Each of these neural networks furnishes a segmental ...

Choice of the phonetic units speech recognizer is a factor greatly affecting the system performance. Phonetic units are normally defined according to the acoustic properties of a speech. Nevertheless, with the limit of training data, too delicate acoustic properties are ignored. Syllable structure is one of the properties usually ignored in English phonetic units due to a lot of possible onsets...

Phonetic baseforms are the basic recognition units in most large vocabulary speech recognition systems. These baseforms are usually determined by hand once a vocabulary is chosen and not modified thereafter. However, many applications of speech recognition, such as dictation transcription, are hampered by a fixed vocabulary and require the user be able to add new words to the vocabulary. At lea...

We present the concept of a "Segmental Neural Net" (SNN) for phonetic modeling in continuous speech recognition. The SNN takes as input all the frames of a phonetic segment and gives as output an estimate of the probability of each of the phonemes, given the input segment. By taking into account all the frames of a phonetic segment simultaneously, the SNN overcomes the wellknown conditional-ind...