An MDL-based approach to extracting subword units for grapheme-to-phoneme conversion
نویسندگان
چکیده
We address a key problem in grapheme-tophoneme conversion: the ambiguity in mapping grapheme units to phonemes. Rather than using single letters and phonemes as units, we propose learning chunks, or subwords, to reduce ambiguity. This can be interpreted as learning a lexicon of subwords that has minimum description length. We implement an algorithm to build such a lexicon, as well as a simple decoder that uses these subwords.
منابع مشابه
Grapheme-Based Automatic Speech Recognition Using KL-HMM
The state-of-the-art automatic speech recognition (ASR) systems typically use phonemes as subword units. In this work, we present a novel grapheme-based ASR system that jointly models phoneme and grapheme information using Kullback-Leibler divergence-based HMM system (KL-HMM). More specifically, the underlying subword unit models are grapheme units and the phonetic information is captured throu...
متن کاملImproving grapheme-based ASR by probabilistic lexical modeling approach
There is growing interest in using graphemes as subword units, especially in the context of the rapid development of hidden Markov model (HMM) based automatic speech recognition (ASR) system, as it eliminates the need to build a phoneme pronunciation lexicon. However, directly modeling the relationship between acoustic feature observations and grapheme states may not be always trivial. It usual...
متن کاملGrapheme based speech recognition
Large vocabulary speech recognition systems traditionally represent words in terms of subword units, usually phonemes. This paper investigates the potential of graphemes acting as subunits. In order to develop context dependent grapheme based speech recognizers several decision tree based clustering procedures are performed and compared to each other. Grapheme based speech recognizers in three ...
متن کاملUsing Auxiliary Sources of Knowledge for Automatic Speech Recognition
Standard hidden Markov model (HMM) based automatic speech recognition (ASR) systems usually use cepstral features as acoustic observation and phonemes as subword units. Speech signal exhibits wide range of variability such as, due to environmental variation, speaker variation. This leads to different kinds of mismatch, such as, mismatch between acoustic features and acoustic models or mismatch ...
متن کاملGrapheme-to-phoneme Conv Morphologica
This paper presents a new approach for grapheme-to-phoneme conversion based on morphology. With this approach, a high accuracy can be obtained, although not for all words a transcription is achieved. The principle of this approach is to automatically decompose an existing pronunciation lexicon into morpheme-similar units called pseudo-morphological units. The pronunciation of the pseudo-morphol...
متن کامل