Japanese large-vocabulary continuous-speech recognition using a newspaper corpus and broadcast news

Ohtsuki, Katsutoshi; Matsuoka, Tatsuo; Mori, Takeshi; Yoshida, Kotaro; Taguchi, Yuichi; Furui, Sadaoki; Shirai, Katsuhiko

doi:10.1016/s0167-6393(99)00006-0

Cited by 11 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also trained a random forest classifier and an LDA classifier with the same data and reported an overall accuracy of 63% for both. We observed better performance for the SVM classifier 5 . The experimentation are based on speech data of ten speakers including both native/non-native, male/female speakers of different age.…”

Section: Discussionmentioning

confidence: 67%

“…For P number of words, we get a P × P matrix. (5) For this confusion matrix, CM , the diagonal entries show the correct word recognition i.e. m ij for i = j.…”

Section: Confusion Matrixmentioning

confidence: 99%

“…The field of ASR has observed tremendous developments during the past few decades (for developed languages, in particular). These include ASR systems for English, French, Mandarin and Japanese [1][2][3][4][5]. For languages which are not rich in terms of available computational linguistics resources, the research is still less mature.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Speech Recognition of Urdu Digits with Optimal Classification Approach

Ali¹,

An²,

Iqbal³

2015

IJCA

View full text Add to dashboard Cite

Speech Recognition for Urdu language is an interesting and less developed task. This is primarily due to the fact that linguistic resources such as rich corpus are not available for Urdu. Yet, few attempts have been made for developing Urdu speech recognition frameworks using the traditional approaches such as Hidden Markov Models and Neural Networks. In this work, we investigate the use of three classification methods for Urdu speech recognition task. We extract the Mel Frequency Cepstral Coefficients, the delta and delta-delta features from the speech data and train the classifiers to perform Urdu speech recognition. We present the performance achieved by training a Support Vector Machine (SVM) classifier, a random forest (RF) classifier and a linear discriminant analysis classifier (LDA) for comparison with SVM. Consequently, the experimental results show that SVM gives better performance than RF and LDA classifiers on this particular task.

show abstract

Section: Discussionmentioning

confidence: 67%

“…For P number of words, we get a P × P matrix. (5) For this confusion matrix, CM , the diagonal entries show the correct word recognition i.e. m ij for i = j.…”

Section: Confusion Matrixmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Speech Recognition of Urdu Digits with Optimal Classification Approach

Ali¹,

An²,

Iqbal³

2015

IJCA

View full text Add to dashboard Cite

show abstract

“…With the latter they filtered out the ungrammatical combinations (incorrect sub-word order), and with a basic trigram sub-word language model the error rate decreased by 18%, relatively. Similar methods were also applied on other agglutinative and tonal languages such as Korean (Choi et al, 2004, Kwon andPark, 2003), Japanese (Ohtsuki et al, 1999) or Turkish (Cilingir, 2003, Erdogan et al, 2005. All these languages have common characteristic of rapid growth in vocabulary and with it OOV words.…”

Section: Introductionmentioning

confidence: 99%

Large vocabulary continuous speech recognition of an inflected language using stems and endings

Rotovnik

Maučec

Kačič

2007

Speech Communication

View full text Add to dashboard Cite

“…In fact for languages whose words are not clearly delimited inside sentences such as Japanese [1], or with words with some structure within them such as Finish, German, Basque etc., these alternative units seem to be more accurate. There have been several proposals for alternative LUs, such as morphemes [1], automatically selected nonword units [2], etc. Thus, taking into account the morphological structure of Basque, the use of morphemes seems to be an appropriate approach.…”

Section: Introductionmentioning

confidence: 99%

Selection of Lexical Units for Continuous Speech Recognition of Basque

Ipiña¹,

Graña²,

Ezeiza

et al. 2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The selection of appropriate Lexical Units (LUs) is an important issue in the development of Continuous Speech Recognition (CSR) systems. Words have been used classically as the recognition unit in most of them. However, proposals of non-word units are beginning to arise. Basque is an agglutinative language with some structure inside words, for which non-word morpheme like units could be an appropriate choice. In this work a statistical analysis of units obtained after morphological segmentation has been carried out. This analysis shows a potential gain of confusion rates in CSR systems, due to the growth of the set of acoustically similar and short morphemes. Thus, several proposals of Lexical Units are analysed to deal with the problem. Measures of Phonetic Perplexity and Speech Recognition rates have been computed using different sets of units and, based on these measures, a set of alternative non-word units have been selected.

show abstract

Japanese large-vocabulary continuous-speech recognition using a newspaper corpus and broadcast news

Cited by 11 publications

References 19 publications

Automatic Speech Recognition of Urdu Digits with Optimal Classification Approach

Automatic Speech Recognition of Urdu Digits with Optimal Classification Approach

Large vocabulary continuous speech recognition of an inflected language using stems and endings

Selection of Lexical Units for Continuous Speech Recognition of Basque

Contact Info

Product

Resources

About