Hsin-Min Wang

Learn More
This paper presents an eigenspace-based fast speaker adaptation approach which can improve the modeling accuracy of the conventional maximum likelihood linear regression (MLLR) techniques when only very limited adaptation data is available. The proposed eigenspace-based MLLR approach was developed by introducing a priori knowledge analysis on the training(More)
The prosody of fluent connected speech is much more complicated than concatenating individual sentence intonations into strings. Prosody framework and modeling should base on more understanding of both the production and perception of fluent speech. We analyzed speech corpora of read Mandarin Chinese discourses from a top-down perspective on perceived units(More)
This correspondence presents the first known results of complete recognition of continuous Mandarin speech for the Chinese language with very large vocabulary but very limited training data. Various acoustic and linguistic processing techniques were developed, and a prototype system of a continuous speech Mandarin dictation machine has been successfully(More)
In this paper, we investigate the problem of automatic singer identification, detection and tracking in popular music recordings with one or multiple singers. This problem reflects an important issue in multimedia applications that require the transcription and indexing of music data to meet the increasing demand for content-based information retrieval. The(More)
This paper describes theMandarin–English Information (MEI) project, wherewe investigated the problemof cross-language spoken document retrieval (CL-SDR), and developed one of the first English–Chinese CL-SDR systems.Our systemaccepts an entireEnglish news story (text) asquery, and retrieves relevantChinese broadcast news stories (audio) from the document(More)
The MATBN Mandarin Chinese broadcast news corpus contains a total of 198 hours of broadcast news from the Public Television Service Foundation (Taiwan) with corresponding transcripts. The primary purpose of this collection is to provide training and testing data for continuous speech recognition evaluation in the broadcast news domain. In this paper, we(More)
With the rapidly growing use of the audio and multimedia information over the Internet, the technology for retrieving speech information using voice queries is becoming more and more important. In this paper, considering the monosyllabic structure of the Chinese language, a whole class of syllable-based indexing features, including overlapping segments of(More)
Label powerset (LP) method is one category of multi-label learning algorithm. This paper presents a basis expansions model for multi-label classification, where a basis function is a LP classifier trained on a random k-labelset. The expansion coefficients are learned to minimize the global error between the prediction and the ground truth. We derive an(More)
In this paper, we proposed an algorithm used to improve the performance of the metric-based segmentation techniques, by which the segmentation points are found at maxima of a distance measured between two contiguous windows shifted along the stream of speech features. In our proposed method, the PCA processes are first performed on the speech features to(More)
This paper presents an effective technique for automatically clustering undocumented music recordings based on their associated singer. This serves as an indispensable step towards indexing and content-based information retrieval of music by singer. The proposed clustering system operates in an unsupervised manner, in which no prior information is available(More)