• KIISE Transactions on Computing Practices
• /
• v.20 no.11
• /
• pp.579-585
• /
• 2014

A phoneme is the minimal unit of speech, and it plays a very important role in speech recognition. This paper proposes a novel method that can be used to recognize 'ㅅ', 'ㅈ', and 'ㅊ' among Korean phonemes. The proposed method is based on a volatility indicator and a turning point indicator that are calculated for each constituting block of the input speech signal. The volatility indicator is the sum of the differences between the values of each two samples adjacent in a block, and the turning point indicator is the number of extremal points at which the direction of the increment or decrement of the values of the sample are inverted in a block. A phoneme recognition algorithm combines the two indicators to finally determine the positions at which the three target phonemes mentioned above are recognized by utilizing optimized thresholds related with those indicators. The experimental results show that the proposed method can markedly reduce the error rate of the existing methods both in terms of the false reject rate and the false accept rate.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.483-489
• /
• 2020

This paper proposes acoustic model training using self-attention for low-resource speech recognition. In low-resource speech recognition, it is difficult for acoustic model to distinguish certain phones. For example, plosive /d/ and /t/, plosive /g/ and /k/ and affricate /z/ and /ch/. In acoustic model training, the self-attention generates attention weights from the deep neural network model. In this study, these weights handle the similar pronunciation error for low-resource speech recognition. When the proposed method was applied to Time Delay Neural Network-Output gate Projected Gated Recurrent Unit (TNDD-OPGRU)-based acoustic model, the proposed model showed a 5.98 % word error rate. It shows absolute improvement of 0.74 % compared with TDNN-OPGRU model.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.5
• /
• pp.213-221
• /
• 2006

Phone segmentation of speech waveform is especially important for concatenative text to speech synthesis which uses segmented corpora for the construction of synthetic units. because the quality of synthesized speech depends critically on the accuracy of the segmentation. In the beginning. the phone segmentation was manually performed. but it brings the huge effort and the large time delay. HMM-based approaches adopted from automatic speech recognition are most widely used for automatic segmentation in speech synthesis, providing a consistent and accurate phone labeling scheme. Even the HMM-based approach has been successful, it may locate a phone boundary at a different position than expected. In this paper. we categorized adjacent phoneme pairs and analyzed the mismatches between hand-labeled transcriptions and HMM-based labels. Then we described the dominant error patterns that must be improved for the speech synthesis. For the experiment. hand labeled standard Korean speech DB from ETRI was used as a reference DB. Time difference larger than 20ms between hand-labeled phoneme boundary and auto-aligned boundary is treated as an automatic segmentation error. Our experimental results from female speaker revealed that plosive-vowel, affricate-vowel and vowel-liquid pairs showed high accuracies, 99%, 99.5% and 99% respectively. But stop-nasal, stop-liquid and nasal-liquid pairs showed very low accuracies, 45%, 50% and 55%. And these from male speaker revealed similar tendency.