Chen, B., Want, H.M., Lee, L.S. Retrieval of broadcast news speech in Mandarin Chinese collected in Taiwan using syllable-level statistical characteristics. Proc. IEEE Intl. Conf. on Acoustics Speech and Signal Processing (ICASSP), 2000. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Sub-Syllabic Acoustic Modeling across Chinese Dialects - Lo, Meng, Ching (2000) (Correct)
....a set of acoustic units which can be used to index Chinese spoken documents with high efficacy. In this study, we used a variety of syllable based acoustic models for indexing Chinese audio, because such units should be able to fully index the audio and circumvent the out ofvocabulary problem [1, 2, 3]. 2 PROPERTIES OF CHINESE We work with two key dialects of the Chinese language Mandarin (or Putonghua) the official spoken language used in China; as well as Cantonese, the commonly used language in Hong Kong and Macau. Both Mandarin and Cantonese are based on the same writing system with ....
CHEN, B. et. al., Retrieval of broadcast news speech in Mandarin Chinese collected in Taiwan using syllable-level statistical characteristics, ICASSP
Mandarin-English Information (MEI): Investigating.. - Meng, Chen.. (2000) Self-citation (Chen Wang) (Correct)
No context found.
Chen, B., H.M. Wang, and L.S. Lee, "Retrieval of Broadcast News Speech in Mandarin Chinese Collected in Taiwan using Syllable-Level Statistical Characteristics," Proceedings of ICASSP, 2000.
Content-based Language Models for Spoken Document Retrieval - Wang, Chen Self-citation (Chen Wang) (Correct)
....quantities of spoken audio are becoming available on the web. Therefore, intelligent and efficient information retrieval techniques allowing easy access to spoken documents, such as the radio and television shows, are becoming highly desired and have been extensively studied in recent years [1 6]. There have been several different approaches developed for spoken document retrieval (SDR) Word based retrieval approaches [1 3] have been very popular and successful, though with the potential problems of either having to know the query words in advance, or requiring a large enough lexicon to ....
....Word based retrieval approaches [1 3] have been very popular and successful, though with the potential problems of either having to know the query words in advance, or requiring a large enough lexicon to cover the growing dynamic contents, such as the diverse broadcast news. Some other researchers [4 6] proposed the concept of subword based approaches because the subword units could provide a complete phonological coverage for spoken documents and circumvent the OOV problem in audio indexing and retrieval. In either approach, applying language models to speech recognition can definitely improve ....
[Article contains additional citation context not shown here]
Chen, B., Wang, H. M. and Lee, L. S. Retrieval of broadcast news speech in Mandarin Chinese collected in Taiwan using syllable-level statistical characteristics. In Proceedings of the
Fast Speaker Adaptation Using Eigenspace-Based Maximum.. - Chen, Liau, Wang, Lee (2000) (5 citations) Self-citation (Chen Wang) (Correct)
....remove the channel effect of the features. Baseline gender independent (GI) SI model was trained with the training set which contains 54 female and 55 male speakers. Considering the monosyllabic structure of Chinese language in which each syllable can be decomposed into an INITIAL FINAL format [6], 112 right context dependent INITIALs along with 38 context independent FINALs were used as the acoustic units for SI model training. Each INITIAL is represented by an HMM with 2 or 3 states, while each FINAL is represented with 4 states. The mixture number per state ranges from 1 to 8, depending ....
B. Chen, H. M. Wang & L. S. Lee, "Retrieval of Broadcast News Speech In Mandarin Chinese Collected In Taiwan Using Syllable-Level Statistical Characteristics", Proc. ICASSP2000, pp.2985-2988, 2000.
Mandarin-English Information (MEI): Investigating.. - Meng, Khudanpur.. (2000) Self-citation (Wang) (Correct)
....in retrieval performance over syllable unigrams, producing retrieval performance competitive 9 The lexicon size of a typical large vocabulary continuous speech recognizer can range from 10,000 to 100,000 word forms. with that obtained using automatically tokenized Chinese words. The study in [Chen, Wang and Lee, 2000] also used syllable pairs with skipped syllables in between. This is because many Chinese abbreviations are derived from skipping characters, e.g. National Science Council can be abbreviated as (including only the first, third and the last characters) Moreover, synonyms often differ by one or ....
Chen, B., H.M. Wang, and L.S. Lee, "Retrieval of Broadcast News Speech in Mandarin Chinese Collected in Taiwan using Syllable-Level Statistical Characteristics," Proceedings of ICASSP, 2000.
Mandarin-English Information (MEI) - Meng, Khudanpur, Oard, Wang (2000) Self-citation (Wang) (Correct)
No context found.
Chen, B., H.M. Wang, and L.S. Lee, "Retrieval of Broadcast News Speech in Mandarin Chinese Collected in Taiwan using Syllable-Level Statistical Characteristics," Proceedings of ICASSP-2000.
Mitsubishi Electric Research Laboratories - Http Www Merl (2004) (Correct)
No context found.
Chen, B., Want, H.M., Lee, L.S. Retrieval of broadcast news speech in Mandarin Chinese collected in Taiwan using syllable-level statistical characteristics. Proc. IEEE Intl. Conf. on Acoustics Speech and Signal Processing (ICASSP), 2000.
A Speech-In List-Out Approach to Spoken User Interfaces - Divi, Forlines, Van.. (2004) (Correct)
No context found.
Chen, B., Want, H.M., Lee, L.S. Retrieval of broadcast news speech in Mandarin Chinese collected in Taiwan using syllable-level statistical characteristics. Proc. IEEE Intl. Conf. on Acoustics Speech and Signal Processing (ICASSP), 2000.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC