The CU-MFEC corpus for Thai and english spelling speech recognition

Kertkeidkachorn, Natthawut; Chanjaradwichai, Supadaech; Suri, Teera; Likitsupin, Krerksak; Vorapatratorn, Surapol; Hirankan, Pawanrat; Limpanadusadee, Worasa; Chuetanapinyo, Supakit; Pitakpawatkul, Kitanan; Puangsri, Natnarong; Tangsirirat, Nathacha; Trakulsuk, Konlawachara; Punyabukkana, Proadpran; Suchato, Atiwong

doi:10.1109/icsda.2012.6422471

Cited by 2 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though proposed approaches are successful and provide reasonable results [Rabiner 1989;Glass 2003;Sung and Jurafsky 2009], the results are still not satisfying for some applications, for example, the spelling speech recognition application [Kertkeidkachorn et al 2012a[Kertkeidkachorn et al , 2014a. Without considering tone information, performances of ASR systems degrade significantly due to lexical ambiguity of words.…”

Section: Introductionmentioning

confidence: 99%

Acoustic Features for Hidden Conditional Random Fields--Based Thai Tone Classification

Kertkeidkachorn

Punyabukkana

Suchato

2015

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

Self Cite

View full text Add to dashboard Cite

In the Thai language, tone information is necessary for Thai speech recognition systems. Previous studies show that many acoustic cues are attributed to shapes of tones. Nevertheless, most Thai tone classification studies mainly adopted F 0 values and their derivatives without considering other acoustic features. In this article, other acoustic features for Thai tone classification are investigated. In the experiment, energy values and spectral information represented by three spectral-based features including the LPC-based feature, PLP-based feature, and MFCC-based feature are applied to the HCRF-based Thai tone classification, which was reported as the best approach for Thai tone classification. The energy values provide an error rate reduction of 22.40% in the isolated word scenario, while there are slight improvements in the continuous speech scenario. On the contrary, spectral-based features greatly contribute to Thai tone classification in the continuous-speech scenario, whereas spectral-based features slightly degrade performances in the isolatedword scenario. The best achievement in the continuous-speech scenario is obtained from the PLP-based feature, which yields an error rate reduction of 13.90%. Therefore, findings in this article are that energy values and spectral-based features, especially the PLP-based feature, are the main contributors to the improvement of the performances of Thai tone classification in the isolated-word scenario and the continuousspeech scenario, respectively.

show abstract