N-gram adaptation using Dirichlet class language model based on part-of-speech for speech recognition

Hatami, Ali; Akbari, Ahmad; Nasersharif, Babak

doi:10.1109/iraniancee.2013.6599642

Cited by 7 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most popular solutions published in the literature, relate to the application of N-gram language models for word-based speech recognition tasks [56][57][58][59]. …”

Section: Example Of Practical Application Of the Obtained Results Formentioning

confidence: 99%

Statistical analysis of orthographic and phonemic language corpus for word-based and phoneme-based Polish language modelling

Kłosowski

2017

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

This article presents the original results of Polish language statistical analysis, based on the orthographic and phonemic language corpus. Phonemic language corpus for Polish was developed by using automatic grapheme-to-phoneme conversion of the source orthographic language corpus, obtained from the National Corpus of Polish (NCP). The corpus contains the most frequently used Polish words, written with the use of phonemic notation. Performed statistical analysis of Polish language based on phonemic language corpus, includes frequency of occurrence calculation of the orthographic and phonemic language components, as well as their sequence. Statistical language data, obtained as a result of performed statistical analysis, enable to develop statistical word-based and phoneme-based language models for Polish. Applying these language models can effectively contribute to efficiency improvement of automatic speech recognition for Polish.

show abstract

“…The most popular solutions published in the literature, relate to the application of N-gram language models for word-based speech recognition tasks [56][57][58][59]. …”

Section: Example Of Practical Application Of the Obtained Results Formentioning

confidence: 99%

Statistical analysis of orthographic and phonemic language corpus for word-based and phoneme-based Polish language modelling

Kłosowski

2017

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

show abstract

“…Unigram (N), bigram (N=2), trigram (N=3), and so on are all examples of N-grams. Bigram model N=2 predicts a term occurring based on the previous single word (N-1) and bigram model N=3 forecasts a term phenomenon based on the previous two terms (N-2) (N-2) (Ito and Kohda, 1996;Hatami, Akbari and Nasersharif, 2013).…”

Section: N -Grammentioning

confidence: 99%

Development of Malaysian English Large Vocabulary Continuous Speech Recognizer using Acoustic Model Adaptation

Yoong¹,

Hong²

2021

Conference Proceedings: International Conference on Digital Transformation and Applications (ICDXA 2021)

View full text Add to dashboard Cite

This research project aims to develop Malaysian English Continuous Speech Recognition system by adapting US English acoustic model with Malaysian English speech corpus using Maximum a posteriori reasoning (MAP) and Maximum Likelihood Linear Regression (MLLR). During feature extraction stage, the Mel-Frequency Cepstral Coefficients (MFCC) technique was used. The Hidden Markov Model was used as the back end pattern comparison technique. For the purpose of implementation, the CMU Sphinx toolkit, which includes Pocketsphinx and Sphinxtrain as well as an acoustic model, was used to develop a speech recognition system for Malaysian English. Malaysian English speech sample will be recorded and transcribed to produce the training database required for acoustic model adaptation. The adaptation speech corpus were collected from a number of speakers. The outcome of this research could increase the application of Malaysian English speech recognition in Malaysia due to accent problem. The graphical user interface for Malaysian English Speech Recognition system was created with PyCharm Community Edition and Python 3.9 to make it easier for the individual consumer usage. As a result, speech recognition systems that have gone through the MAP adaptation had the best performance. Its average word error rate achieved was 32.84%. average word recognition rate was 72.52% and average sentence error rate was 78.89%. Keywords: Speech Recognition, Acoustic Model, MAP, MLLR, Pocketsphinx

show abstract

“…In our proposed model, we use POS information of previous words along with history words for word clustering. Similar to DCLM, we declared a linear discriminant function [9]. (10) This function represents the class posterior probability where .…”

Section: A Dirichlet Class Language Model Based On Part-ofspeechmentioning

confidence: 99%

“…2, to predict the class mixtures , are constructed from the history factors and the class sequence . Based on the CDCLM_POS, the probability of an -gram event is generated using: (13) where all of parameters are as in (9).…”

Section: B Cache Dirichlet Class Language Model Based On Partof-speechmentioning

confidence: 99%

Factored language model adaptation using Dirichlet class language model for speech recognition

Hatami

Akbari

Nasersharif³

2013

The 5th Conference on Information and Knowledge Technology

Self Cite

View full text Add to dashboard Cite

Language model (LM) is essential for speech recognition systems. Efficiency of this model depends on its adaptation to the linguistic characteristics. According to this, adaptation methods attempt to use syntactic and semantic features for language modelling. The previous adaptation methods such as family of Dirichlet class language model (DCLM) exploit class of history words. These methods due to lake of syntactic information are not appropriate for high morphology languages such as Farsi. This paper presents an overview for using syntactic information such as part-of-speech (POS) in DCLM for combining with a factored language model (FLM). In our proposed idea, word clustering is based on POS of previous words and history words. Different LMs are experimentally evaluated using the BijanKhan corpus. The experiments indicate that use of POS information along with history words and class of history words improves FLM, and reduces the perplexity on our corpus. Moreover, LMs are evaluated using the Farsdat corpus in hidden Markov model based on automatic speech recognition (ASR) system. Exploiting POS information along with DCLM achieved relative gain of word error rate of the ASR system by 1.2% over the DCLM.

show abstract

N-gram adaptation using Dirichlet class language model based on part-of-speech for speech recognition

Cited by 7 publications

References 10 publications

Statistical analysis of orthographic and phonemic language corpus for word-based and phoneme-based Polish language modelling

Statistical analysis of orthographic and phonemic language corpus for word-based and phoneme-based Polish language modelling

Development of Malaysian English Large Vocabulary Continuous Speech Recognizer using Acoustic Model Adaptation

Factored language model adaptation using Dirichlet class language model for speech recognition

Contact Info

Product

Resources

About