An efficient way to develop large scale speech corpora is to collect phonetically rich ones that have high coverage of phonetic contextual units. The sentence set, usually called as the minimum set, should have small text size in order to reduce the collection cost. It can be selected by a greedy search algorithm from a large mother text corpus. With the inclusion of more and more phonetic contextual effects, the number of different phonetic contextual units increased dramatically, making the search not a trivial issue. In order to improve the search efficiency, we previously proposed a so-called least-to-most-ordered greedy search based on the conventional algorithms. This paper evaluated these algorithms in order to show their different characteristics. The experimental results showed that the least-to-most-ordered methods successfully achieved smaller objective sets at significantly less computation time, when compared with the conventional ones. This algorithm has already been applied to the development a number of speech corpora, including a large scale phonetically rich Chinese speech corpus ATRPTH which played an important role in developing our multi-language translation system.

This paper presents a study on modeling inter-word pauses to improve the robustness of acoustic models for recognizing noisy conversational speech. When precise contextual modeling is used for pauses, the frequent appearances and varying acoustics of pauses in noisy conversational speech make it a problem to automatically generate an accurate phonetic transcription of the training data for developing robust acoustic models. This paper presents a proposal to exploit the reliable phonetic heuristics of pauses in speech to aid the detection of varying pauses. Based on it, a stepwise approach to optimize pause HMMs was applied to the data of the DARPA SPINE2 project, and more correct phonetic transcription was achieved. The cross-word triphone HMMs developed using this method got an absolute 9.2% word error reduction when compared to the conventional method with only context free modeling of pauses. For the same pause modeling method, the use of the optimized phonetic segmentation brought about an absolute 5.2% improvements.

A method was developed for automatic recognition of syllable tone types in continuous speech of Mandarin by integrating two techniques, tone nucleus modeling and neural network classifier. The tone nucleus modeling considers a syllable F0 contour as consisting of three parts: onset course, tone nucleus, and offset course. Two courses are transitions from/to neighboring syllable F0 contours, while the tone nucleus is intrinsic part of the F0 contour. By viewing only the tone nucleus, acoustic features less affected by neighboring syllables are obtained. When using the tone nucleus modeling, automatic detection of tone nucleus comes crucial. An improvement was added to the original detection method. Distinctive acoustic features for tone types are not limited to F0 contours. Other prosodic features, such as waveform power and syllable duration, are also useful for tone recognition. Their heterogeneous features are rather difficult to be handled simultaneously in hidden Markov models (HMM), but are easy in neural networks. We adopted multi-layer perceptron (MLP) as a neural network. Tone recognition experiments were conducted for speaker dependent and independent cases. In order to show the effect of integration, experiments were conducted also for two baselines: HMM classifier with tone nucleus modeling, and MLP classifier viewing entire syllable instead of tone nucleus. The integrated method showed 87.1% of tone recognition rate in speaker dependent case, and 80.9% in speaker independent case, which was about 10% relative error reduction as compared to the baselines.

Chinese is a representative tonal language, and it has been an attractive topic of how to process tone information in the state-of-the-art large vocabulary speech recognition system. This paper presents a novel way to derive an efficient phoneme set of tone-dependent units to build a recognition system, by iteratively merging a pair of tone-dependent units according to the principle of minimal loss of the Mutual Information (MI). The mutual information is measured between the word tokens and their phoneme transcriptions in a training text corpus, based on the system lexical and language model. The approach has a capability to keep discriminative tonal (and phoneme) contrasts that are most helpful for disambiguating homophone words due to lack of tones, and merge those tonal (and phoneme) contrasts that are not important for word disambiguation for the recognition task. This enables a flexible selection of phoneme set according to a balance between the MI information amount and the number of phonemes. We applied the method to traditional phoneme set of Initial/Finals, and derived several phoneme sets with different number of units. Speech recognition experiments using the derived sets showed its effectiveness.