• MALSORI
• /
• no.47
• /
• pp.131-140
• /
• 2003

We propose a new method of generating client models for HMM based text-dependent speaker verification system with only a small amount of training data. To make a client model, statistical methods such as segmental K-means algorithm are widely used, but they do not guarantee the quality or reliability of a model when only limited data are avaliable. In this paper, we propose a blind speech segmentation based on level building DTW algorithm as an alternative method to make a client model with limited data. In addition, considering the fact that voiced sounds have much more speaker-specific information than unvoiced sounds and energy of the former is higher than that of the latter, we also propose a new score evaluation method using the observation probability raised to the power of weighting factor estimated from the normalized log energy. Our experiment shows that the proposed methods are superior to conventional HMM based speaker verification system.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.4
• /
• pp.636-644
• /
• 1990

Hidden Markov models(HMM's) have been known to be useful representation for speech signal and are used in a wide variety of speech systems. For speech recognition applications, it is desirable to incorporate durational information of states in model which correspond to phonetic duration of speech segments. In this paper we propose duration-dependent HMM's that include durational information of states appropriately for the left-to-right model. Reestimation formulae for the parameters of the proposed model are derived and their convergence is verified. Finally, the performance of the proposed models is verified by applying to an isolated word, speaker independent speech recognition system.

• MALSORI
• /
• no.60
• /
• pp.109-123
• /
• 2006

Since computing the log-likelihood of Gaussian mixture density is a major computational burden for the speech recognizer based on the continuous HMM, several techniques have been proposed to reduce the number of mixtures to be used for recognition. In this paper, we propose a modified Bucket Box Intersection (BBI) algorithm, in which two relative thresholds are employed: one is the relative threshold in the conventional BBI algorithm and the other is used to reduce the number of the Gaussian boxes which are intersected by the hyperplanes at the boxes' edges. The experimental results show that the proposed algorithm reduces the number of Gaussian mixtures by 12.92% during the recognition phase with negligible performance degradation compared to the conventional BBI algorithm.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.123-126
• /
• 2003

We discuss how to reduce the number of inverse matrix and its dimensions requested in MLLR framework for speaker adaptation. To find a smaller set of variables with less redundancy, we employ PCA(principal component analysis) and ICA(independent component analysis) that would give as good a representation as possible. The amount of additional computation when PCA or ICA is applied is as small as it can be disregarded. The dimension of HMM parameters is reduced to about 1/3 ~ 2/7 dimensions of SI(speaker independent) model parameter with which speech recognition system represents word recognition rate as much as ordinary MLLR framework. If dimension of SI model parameter is n, the amount of computation of inverse matrix in MLLR is proportioned to O($n^4$). So, compared with ordinary MLLR, the amount of total computation requested in speaker adaptation is reduced to about 1/80~1/150.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.4E
• /
• pp.112-119
• /
• 2004

This paper presents a method for the automatic recognition of pitch accents with no prior knowledge about the phonetic content of the signal (no knowledge of word or phoneme boundaries or of phoneme labels). The recognition algorithm used in this paper is a time-delay recurrent neural network (TDRNN). A TDRNN is a neural network classier with two different representations of dynamic context: delayed input nodes allow the representation of an explicit trajectory F0(t), while recurrent nodes provide long-term context information that can be used to normalize the input F0 trajectory. Performance of the TDRNN is compared to the performance of a MLP (multi-layer perceptron) and an HMM (Hidden Markov Model) on the same task. The TDRNN shows the correct recognition of $91.9{\%}\;of\;pitch\;events\;and\;91.0{\%}$ of pitch non-events, for an average accuracy of $91.5{\%}$ over both pitch events and non-events. The MLP with contextual input exhibits $85.8{\%},\;85.5{\%},\;and\;85.6{\%}$ recognition accuracy respectively, while the HMM shows the correct recognition of $36.8{\%}\;of\;pitch\;events\;and\;87.3{\%}$ of pitch non-events, for an average accuracy of $62.2{\%}$ over both pitch events and non-events. These results suggest that the TDRNN architecture is useful for the automatic recognition of pitch accents.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.1E
• /
• pp.20-24
• /
• 2006

In this paper, we focused on the real time implementation of a speech recognition system with medium size of vocabulary considering its application to a mobile phone. First, we developed the PC based variable vocabulary word recognizer having the size of program memory and total acoustic models as small as possible. To reduce the memory size of acoustic models, linear discriminant analysis and phonetic tied mixture were applied in the feature selection process and training HMMs, respectively. In addition, state based Gaussian selection method with the real time cepstral normalization was used for reduction of computational load and robust recognition. Then, we verified the real-time operation of the implemented recognition system on the TMS320C6201 EVM board. The implemented recognition system uses memory size of about 610 kbytes including both program memory and data memory. The recognition rate was 95.86% for ETRI 445DB, and 96.4%, 97.92%, 87.04% for three kinds of name databases collected through the mobile phones.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.2
• /
• pp.49-57
• /
• 1997

In this paper, we propose the stochastic pronunciation lexicon model for large vocabulary continuous speech recognition system. We can regard stochastic lexicon as HMM. This HMM is a stochastic finite state automata consisting of a Markov chain of subword states and each subword state in the baseform has a probability distribution of subword units. In this method, an acoustic representation of a word can be derived automatically from sample sentence utterances and subword unit models. Additionally, the stochastic lexicon is further optimized to the subword model and recognizer. From the experimental result on 3000 word continuous speech recognition, the proposed method reduces word error rate by 23.6% and sentence error rate by 10% compare to methods based on standard phonetic representations of words.

• MALSORI
• /
• no.49
• /
• pp.123-134
• /
• 2004

An automatic pronunciation correction system provides learners with correction guidelines for each mispronunciation. In this paper we propose an HMM based speech recognizer which automatically classifies pronunciation errors when Koreans speak Japanese. We also propose two pronunciation networks for automatic detection of mispronunciation. In this paper, we evaluated performances of the networks by computing the correlation between the human ratings and the machine scores obtained from the speech recognizer.

• MALSORI
• /
• no.48
• /
• pp.127-139
• /
• 2003

An automatic pronunciation correction system provides learners with correction guidelines for each mispronunciation. In this paper we propose an HMM based speech recognizer which automatically classifies pronunciation errors when Korean speak Japanese. For this purpose we also develop phoneme recognizers for Korean and Japanese. Experimental results show that the machine scores of the proposed recognizer correlate with expert ratings well.

• Proceedings of the KSPS conference
• /
• 2003.10a
• /
• pp.29-32
• /
• 2003

This paper proposes an automatic pronunciation correction system which provides users with correction guidelines for each pronunciation error. For this purpose, we develop an HMM speech recognizer which automatically classifies pronunciation errors when Korean speaks foreign language. And, we collect speech database of native and nonnative speakers using phonetically balanced word lists. We perform analysis of mispronunciation types from the experiment of automatic mispronunciation detection using speech recognizer.