Pure acoustic neural models, particularly the LSTM-RNN model, have shown great potential in language identification (LID). However, the phonetic information has been largely overlooked by most of existing neural LID models, although this information has been used in the conventional phonetic LID systems with a great success. We present a phone-aware neural LID architecture, which is a deep LSTM...

This paper presents a phonetic conversion system with phonological knowledge for Galician. The system allows us to evaluate several phonological processes, like syllabification or phonological derivation, as well as to transcript lexicons with phonetic annotation of different linguistic varieties automatically. The system consists of the following modules: (i) phonological conversion, which gen...

Born with an innate neural architecture built specially for language learning, young children have the ability to distinguish sounds in a variety of languages. As they are exposed to native language environment, perceptual reorganization occurs, and native language system gradually establishes. Phonology knowledge, which is language-specific, emerges during this process. In this study, based on...

To investigate the interaction in speech perception of auditory information and lexical knowledge (in particular, knowledge of which phonetic sequences are words), acoustic continua varying in voice onset time were constructed so that for each acoustic continuum, one of the two possible phonetic categorizations made a word and the other did not. For example, one continuum ranged between the wor...

Learning phonetic categories is one of the first steps to learning a language, yet is hard to do using only distributional phonetic information. Semantics could potentially be useful, since words with different meanings have distinct phonetics, but it is unclear how many word meanings are known to infants learning phonetic categories. We show that attending to a weaker source of semantics, in t...

The main goal of this work is to describe a new model for a large vocabulary continuous speech recognition system using a phonetic-phonological approach. This work proposes a statistical phonetic structure, applied at the phoneticphonological level, to improve the speech recognition performance in systems with phonetic-phonological modeling. It is showed that the general likelihood scores are i...

This paper is concerced with the use of error back-propagation in phonetic classification. Our objective is to investigate the basic characteristics of back-propagation, and study how the framework of multi-layer perceptrons can be exploited in phonetic recognition. We explore issues such as integration of heterogeneous sources of information, conditioll~ that can affect performance of phonetic...

1. I will be arguing from data on vowel shifts in progress, and from principles of language change, that language specific phonetic implementation rules must be part of speaker knowledge, and thus part of language acquisition. Then, I will sketch an abstract model of what phonetic implementation could be like. Having argued these points, I will address how this approach interacts with phonologi...

This paper presents a knowledge/rule based approach to continuous speech recognition. The proposed recognition system (Samouelian, 1994) uses a data driven methodology, where the knowledge about the structure and characteristics of the speech signal is captured explicitly from the database by the use of inductive inference (C4.5) (Quinlan, 1986). This allows the integration of features from exi...

This study is aimed at investigating whether automatic phonetic transcription procedures can approximate manual transcriptions typically delivered with contemporary large speech corpora. To this end, ten automatic procedures were used to generate a broad phonetic transcription of well-prepared speech (read-aloud texts) and spontaneous speech (telephone dialogues) from the Spoken Dutch Corpus. T...