Morpheme-Based Modeling of Pronunciation Variation for Large Vocabulary Continuous Speech Recognition in Korean

Lee, Kyong-Nim; Chung, Minhwa

doi:10.1093/ietisy/e90-d.7.1063

Cited by 11 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the Korean speech corpus uttered by Japanese learners, at first, orthographic transcriptions at word level are manually created by 4 native transcribers who major in Korean linguistics and literature. The corresponding canonical phonetic transcriptions are automatically generated by using a Grapheme-to-Phoneme converter [12] and orthographic word transcriptions. Using canonical phonetic transcriptions as reference, each utterance is manually transcribed to get auditory phonetic transcriptions.…”

Section: Transcriptionsmentioning

confidence: 99%

A corpus-based analysis of Korean segments produced by Japanese learners

Hong,

Kim,

Chung

2013

Speech and Language Technology in Education (SLaTE 2013)

View full text Add to dashboard Cite

This paper examines variations of Korean segments produced by Japanese learners of Korean. For corpus-based statistical analysis, we have used Korean read speech corpus produced by Japanese learners. Contrastive analysis of the target language and the source language is performed to provide information for interpreting the results of corpus analysis. Segmental variations are analyzed by aligning canonical phonetic transcriptions with auditory phonetic transcriptions of the corpus. The results show that (1) Japanese learners tend to demonstrate substitutions due to differences in the phonemic systems of the two languages; and (2) they are likely to omit a consonant or insert a vowel to deal with the different syllable structures. These results with detailed statistical data are useful for designing a computer-assisted pronunciation training and assessment system for Japanese learners of Korean.

show abstract

Section: Transcriptionsmentioning

confidence: 99%

A corpus-based analysis of Korean segments produced by Japanese learners

Hong,

Kim,

Chung

2013

Speech and Language Technology in Education (SLaTE 2013)

View full text Add to dashboard Cite

show abstract

“…In large vocabulary continuous speech recognition, there is a problem that the number of phoneme units is too small to express various acoustic changes. Previous works have confronted this problem using the implicit method [4,5] or the explicit method [6]. Here, we focus on the implicit method using a decision tree [4].…”

Section: Introductionmentioning

confidence: 99%

Acoustic Data-Driven Subword Units Obtained through Segment Embedding and Clustering for Spontaneous Speech Recognition

2020

View full text Add to dashboard Cite

We propose a method to extend a phoneme set by using a large amount of broadcast data to improve the performance of Korean spontaneous speech recognition. In the proposed method, we first extract variable-length phoneme-level segments from broadcast data and then convert them into fixed-length embedding vectors based on a long short-term memory architecture. We use decision tree-based clustering to find acoustically similar embedding vectors and then build new acoustic subword units by gathering the clustered vectors. To update the lexicon of a speech recognizer, we build a lookup table between the tri-phone units and the units derived from the decision tree. Finally, the proposed lexicon is obtained by updating the original phoneme-based lexicon by referencing the lookup table. To verify the performance of the proposed unit, we compare the proposed unit with the previous units obtained by using the segment-based k-means clustering method or the frame-based decision-tree clustering method. As a result, the proposed unit is shown to produce better performance than the previous units in both spontaneous, and read Korean speech recognition tasks.In spontaneous speech recognition, the phoneme unit has a problem of acoustically low discrimination. In more detail, the phoneme unit in spontaneous speech has a smaller inter-unit distance and a larger variance than the phoneme unit in read speech, which is one of the major factors contributing to the decrease in recognition accuracy [7,8]. In general, using a decision tree in the implicit method shows improved speech recognition accuracy when segmented from acoustically discriminative units. This is also confirmed by the fact that a speech recognizer for read speech has shown better performance when segmented based on the phoneme unit instead of the grapheme unit. Thus, if we build an acoustically discriminative unit by clustering common spectral patterns from spontaneous speech, we can expect an improvement in the performance of spontaneous speech recognition.We propose a method to improve the performance of spontaneous speech recognition by extending the phoneme set with a large amount of Korean broadcast data. The proposed unit is extracted in three steps. We first extract variable-length phoneme-level segments and then convert them into fixed-length latent vectors based on a long short-term memory (LSTM) architecture [9]. Finally, we use the decision tree-based clustering algorithm [4,10] to cluster acoustically similar latent vectors and then build a new acoustic subword unit by gathering the clustered vectors. In the unit derivation experiments, we compare the proposed and previous approaches [9,11] in terms of the fixed-length vector extraction and the clustering algorithm. The proposed unit is shown to produce better performance than the acoustic subword units obtained by previous methods, in both spontaneous and read speech recognition tasks.This paper is an extension of our previous conference paper [9] that improves the clustering method from a k-means clusteri...

show abstract

Cross-Word Pronunciation Variations

AbuZeina

Elshafei

2011

SpringerBriefs in Electrical and Computer Engineering

View full text Add to dashboard Cite

Morpheme-Based Modeling of Pronunciation Variation for Large Vocabulary Continuous Speech Recognition in Korean

Cited by 11 publications

References 19 publications

A corpus-based analysis of Korean segments produced by Japanese learners

A corpus-based analysis of Korean segments produced by Japanese learners

Acoustic Data-Driven Subword Units Obtained through Segment Embedding and Clustering for Spontaneous Speech Recognition

Cross-Word Pronunciation Variations

Contact Info

Product

Resources

About