Letter-to-Sound Pronunciation Prediction Using Conditional Random Fields

Wang, Dong; King, Simon

doi:10.1109/lsp.2010.2098440

Cited by 36 publications

(29 citation statements)

References 21 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Statistical models such as decision trees, JointMultigram Model (JMM) [6], or Conditional Random Field (CRF) [7] are used to learn pronunciation rules. All these approaches invariantly assume access to "prior" linguistic resources consisting of sequences of graphemes and their corresponding sequences of phonemes [8]. Writing by hand, this rule is hard and very time consuming.…”

Section: Speech → S P Iy Chmentioning

confidence: 99%

G2PIL: A Grapheme-To-Phoneme Conversion Tool for the Italian Language

Biondi¹,

Catania²,

Natale³

et al. 2015

IJNLC

View full text Add to dashboard Cite

This paper presents a knowledge-based approach for the grapheme to-phoneme conversion (G2P) of isolated words of the Italian language. With more than 7,000 languages in the world, the biggest challenge today is to rapidly port speech processing systems to new languages with low human effort and at reasonable cost. This includes the creation of qualified pronunciation dictionaries. The dictionaries provide the mapping from the orthographic form of a word to its pronunciation, which is useful in both speech synthesis and automatic speech recognition (ASR) systems.For training the acoustic models we need an automatic routine that maps the spelling of training set to a string of phonetic symbols representing the pronunciation.

show abstract

Section: Speech → S P Iy Chmentioning

confidence: 99%

G2PIL: A Grapheme-To-Phoneme Conversion Tool for the Italian Language

Biondi¹,

Catania²,

Natale³

et al. 2015

IJNLC

View full text Add to dashboard Cite

show abstract

“…In general, a G2P is developed using machine learning-based methods, such as instance-based learning [1], table lookup with defaults [1], self-learning techniques [2], hidden Markov model [3], morphology and phoneme history [4], joint multigram models [5], conditional random fields [6], Kullback-Leibler divergence-based hidden Markov model [7]. These methods are commonly very complex and designed to be language independent, but they give varying performances for some phonemically complex languages, such as English, Dutch, French, and Germany.…”

Section: Introductionmentioning

confidence: 99%

Modified Grapheme Encoding and Phonemic Rule to Improve PNNR-Based Indonesian G2P

Suyanto¹,

Hartati²,

Harjoko³

2016

ijacsa

View full text Add to dashboard Cite

Abstract-A grapheme-to-phoneme conversion (G2P) is very important in both speech recognition and synthesis. The existing Indonesian G2P based on pseudo nearest neighbour rule (PNNR) has two drawbacks: the grapheme encoding does not adapt all Indonesian phonemic rules and the PNNR should select a best phoneme from all possible conversions even though they can be filtered by some phonemic rules. In this paper, a modified partial orthogonal binary grapheme encoding and a phonemicbased rule are proposed to improve the performance of PNNRbased Indonesian G2P. Evaluating on 5-fold cross-validation, contain 40K words to develop the model and 10K words to evaluation each, shows that both proposed concepts reduce the relative phoneme error rate (PER) by 13.07%. A more detail analysis shows the most errors are from grapheme ⟨e⟩ that can be dynamically converted into either /E/ or /@/ since four prefixes, 'ber', 'me', 'per', and 'ter', produce many ambiguous conversions with basic words and also from some similar compound words with both different pronunciations for the grapheme ⟨e⟩. A stemming procedure can be applied to reduce those errors.

show abstract

“…Finally, CRFs offer several advantages. They are widely used in grapheme-to-phoneme converters [19,9,14], thus enabling an easy integration of their outputs. And they also allow to explicitly consider and combine a large set of features.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Speaker Pronunciation Adaptation for Spontaneous Speech Synthesis Using Linguistic Features

Qader

Lecorvé

Lolive

et al. 2015

Statistical Language and Speech Processing

View full text Add to dashboard Cite

Abstract. Pronunciation adaptation consists in predicting pronunciation variants of words and utterances based on their standard pronunciation and a target style. This is a key issue in text-to-speech as those variants bring expressiveness to synthetic speech, especially when considering a spontaneous style. This paper presents a new pronunciation adaptation method which adapts standard pronunciations to the style of individual speakers in a context of spontaneous speech. Its originality and strength are to solely rely on linguistic features and to consider a probabilistic machine learning framework, namely conditional random fields, to produce the adapted pronunciations. Features are first selected in a series of experiments, then combined to produce the final adaptation method. Backend experiments on the Buckeye conversational English speech corpus show that adapted pronunciations significantly better reflect spontaneous speech than standard ones, and that even better could be achieved if considering alternative predictions.

show abstract

Letter-to-Sound Pronunciation Prediction Using Conditional Random Fields

Cited by 36 publications

References 21 publications

G2PIL: A Grapheme-To-Phoneme Conversion Tool for the Italian Language

G2PIL: A Grapheme-To-Phoneme Conversion Tool for the Italian Language

Modified Grapheme Encoding and Phonemic Rule to Improve PNNR-Based Indonesian G2P

Probabilistic Speaker Pronunciation Adaptation for Spontaneous Speech Synthesis Using Linguistic Features

Contact Info

Product

Resources

About