Learn More
Tone has a crucial role in Mandarin speech in distinguishing ambiguous words. Most state-of-the-art Mandarin automatic speech recognition systems adopt embedded tone modeling, where tonal acoustic units are used and F0 features are appended to the spectral feature vector. In this paper, we combine the embedded aproach (using improved F0 smoothing) with(More)
The framework of posteriorgram-based template matching has been shown to be successful for query-by-example spoken term detection (STD). This framework employs a tokenizer to convert query examples and test utterances into frame-level posteriorgrams, and applies dynamic time warping to match the query posteriorgrams with test posteriorgrams to locate(More)
Pitch estimation from acoustic signals is a fundamental problem in many areas of speech research. For noise-corrupted speech, reliable pitch estimation is difficult. This paper presents a study of pitch estimation in noisy speech based on robust temporal-spectral representation and sparse reconstruction. We propose to accumulate spectral peaks over(More)
This letter describes a speaker verification system that uses complementary acoustic features derived from the vocal source excitation and the vocal tract system. A new feature set, named the wavelet octave coefficients of residues (WOCOR), is proposed to capture the spectro-temporal source excitation characteristics embedded in the linear predictive(More)
In Chinese languages, tones carry important information at various linguistic levels. This research is based on the belief that tone information, if acquired accurately and utilized effectively, contributes to the automatic speech recognition of Chinese. In particular, we focus on the Cantonese dialect, which is spoken by tens of millions of people in(More)
In this paper, we will present the up-to-date status for the development of several large-scale Cantonese spoken language corpora. These corpora include speech data at different linguistic levels ranging from isolated syllable to continuous passage. This is the first ever effort in compiling a good collection of spoken language resources for research and(More)
-The purpose of this correspondence is to show that an<lb>adaptive weighted recursive least squares algorithm with a variable<lb>forgetting factor (WRLS-VFF) will adjust the size of the data segment to<lb>be analyzed according to its time-varying characteristics, as during the<lb>transitions between vowels and consonants. The algorithm can(More)
Recently the posteriorgram-based template matching framework has been successfully applied to query-by-example spoken term detection tasks for low-resource languages. This framework employs a tokenizer to derive posteriorgrams, and applies dynamic time warping (DTW) to the posteriorgrams to locate the possible occurrences of a query term. Based on this(More)