• Journal of Digital Convergence
• /
• v.11 no.6
• /
• pp.137-142
• /
• 2013

Speech recognition system is input of inaccurate vocabulary by feature extraction case of recognition by appear result of unrecognized or similar phoneme recognized. Therefore, in this paper, we propose a speech recognition error correction method using phoneme similarity rate and reliability measures based on the characteristics of the phonemes. Phonemes similarity rate was phoneme of learning model obtained used MFCC and LPC feature extraction method, measured with reliability rate. Minimize the error to be unrecognized by measuring the rate of similar phonemes and reliability. Turned out to error speech in the process of speech recognition was error compensation performed. In this paper, the result of applying the proposed system showed a recognition rate of 98.3%, error compensation rate 95.5% in the speech recognition.

• Phonetics and Speech Sciences
• /
• v.6 no.2
• /
• pp.29-34
• /
• 2014

In the Vector Taylor Series (VTS)-based noisy speech recognition methods, Hidden Markov Models (HMM) are usually trained with clean speech. However, better performance is expected by training the HMM with noisy speech. In a previous study, we could find that Minimum Mean Square Error (MMSE) estimation of the training noisy speech in the log-spectrum domain produce improved recognition results, but since the proposed algorithm was done in the log-spectrum domain, it could not be used for the HMM adaptation. In this paper, we modify the previous algorithm to derive a novel mathematical relation between test and training noisy speech in the cepstrum domain and the mean and covariance of the Multi-condition TRaining (MTR) trained noisy speech HMM are adapted. In the noisy speech recognition experiments on the Aurora 2 database, the proposed method produced 10.6% of relative improvement in Word Error Rates (WERs) over the MTR method while the previous MMSE estimation of the training noisy speech produced 4.3% of relative improvement, which shows the superiority of the proposed method.

• Speech Sciences
• /
• v.12 no.3
• /
• pp.115-124
• /
• 2005

We investigated on the submission of multiple candidates in speaker-independent speech recognition by VQ/HMM. Submission of fixed number of multiple candidates has first been examined. As the number of candidates increases by two, three, and four, the recognition error rates were found to decrease by 41%, 58%, and 65%, respectively compared to that of a single candidate. We tried another approach that the candidates within a range of Viterbi scores are submitted. The number of candidates showed geometric increase as the admitted range becomes large. For a practical application, a combination of the above two methods was also studied. We chose the candidates within some range of Viterbi scores and limited the maximum number of candidates submitted to five. Experimental results showed that recognition error rates of less than 10% could be achieved with average number of candidates of 3.2 by this method.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.1-7
• /
• 2021

Recently, since most of the research on correcting speech recognition errors is based on English, there is not enough research on Korean speech recognition. Compared to English speech recognition, however, Korean speech recognition has many errors due to the linguistic characteristics of Korean language, such as Korean Fortis and Korean Liaison, thus research on Korean speech recognition is needed. Furthermore, earlier works primarily focused on editorial distance algorithms and syllable restoration rules, making it difficult to correct the error types of Korean Fortis and Korean Liaison. In this paper, we propose a context-sensitive post-processing model of speech recognition using a LSTM-based sequence-to-sequence model and Bahdanau attention mechanism to correct Korean speech recognition errors caused by the pronunciation. Experiments showed that by using the model, the speech recognition performance was improved from 64% to 77% for Fortis, 74% to 90% for Liaison, and from 69% to 84% for average recognition than before. Based on the results, it seems possible to apply the proposed model to real-world applications based on speech recognition.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1137-1142
• /
• 2010

This paper studied the speech parameters less affected by the human emotion for the development of the robust speech recognition system. For this purpose, the effect of emotion on the speech recognition system and robust speech parameters of speech recognition system were studied using speech database containing various emotions. In this study, mel-cepstral coefficient, delta-cepstral coefficient, RASTA mel-cepstral coefficient and frequency warped mel-cepstral coefficient were used as feature parameters. And CMS (Cepstral Mean Subtraction) method were used as a signal bias removal technique. Experimental results showed that the HMM based speaker independent word recognizer using vocal tract length normalized mel-cepstral coefficient, its derivatives and CMS as a signal bias removal showed the best performance of 0.78% word error rate. This corresponds to about a 50% word error reduction as compare to the performance of baseline system using mel-cepstral coefficient, its derivatives and CMS.

• Speech Sciences
• /
• v.13 no.4
• /
• pp.177-186
• /
• 2006

In an effort to enhance the quality of feature vector classification and thereby reduce the recognition error rate of the speaker-independent speech recognition, we employ the Mahalanobis distance in the calculation of the similarity measure between feature vectors. It is assumed that the metric matrix of the Mahalanobis distance be diagonal for the sake of cost reduction in memory and time of calculation. We propose that the diagonal elements be given in terms of the variations of the feature vector components. Geometrically, this prescription tends to redistribute the set of data in the shape of a hypersphere in the feature vector space. The idea is applied to the speech recognition by hidden Markov model with fuzzy vector quantization. The result shows that the recognition is improved by an appropriate choice of the relevant adjustable parameter. The Viterbi score difference of the two winners in the recognition test shows that the general behavior is in accord with that of the recognition error rate.

• MALSORI
• /
• no.44
• /
• pp.115-130
• /
• 2002

Voice input is often required in many new application environments, but the low rate of speech recognition makes it difficult to extend its application. Previous approaches were to raise the accuracy of the recognition by post-processing of the recognition results, which were all lexical-oriented. We suggest a new semantic-oriented approach in speech recognition error correction. Through experiments using a speech-driven in-vehicle telematics information application, we show the excellent performance of our approach and some advantages it has as a semantic-oriented approach over a pure lexical-oriented approach.

• MALSORI
• /
• no.46
• /
• pp.77-86
• /
• 2003

Channel distortion and coarticulation effect in the Korean connected digit telephone speech make it difficult to achieve high performance of connected digit recognition in the telephone environment. In this paper, as a basic research to improve the recognition performance of Korean connected digit telephone speech, recognition error patterns are investigated and analyzed. Korean connected digit telephone speech database released by SiTEC and HTK system are used for recognition experiments. Both DWFBA and MRTCN methods are used for feature extraction and channel compensation, respectively. Experimental results are discussed with our findings.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.71-81
• /
• 2024

Recent advances in deep learning for speech and visual recognition have accelerated the development of multimodal speech recognition, yielding many innovative results. We introduce a Korean audiovisual speech recognition corpus. This dataset comprises approximately 150 h of manually transcribed and annotated audiovisual data supplemented with additional 2000 h of untranscribed videos collected from YouTube under the Creative Commons License. The dataset is intended to be freely accessible for unrestricted research purposes. Along with the corpus, we propose an open-source framework for automatic speech recognition (ASR) and audiovisual speech recognition (AVSR). We validate the effectiveness of the corpus with evaluations using state-of-the-art ASR and AVSR techniques, capitalizing on both pretrained models and fine-tuning processes. After fine-tuning, ASR and AVSR achieve character error rates of 11.1% and 18.9%, respectively. This error difference highlights the need for improvement in AVSR techniques. We expect that our corpus will be an instrumental resource to support improvements in AVSR.

• Phonetics and Speech Sciences
• /
• v.15 no.2
• /
• pp.13-20
• /
• 2023

This study explores the potential of automated speech recognition (ASR) in assessing English learners' pronunciation. We employed ASR technology, acknowledged for its impartiality and consistent results, to analyze speech audio files, including synthesized speech, both native-like English and Korean-accented English, and speech recordings from a native English speaker. Through this analysis, we establish baseline values for the word error rate (WER). These were then compared with those obtained for human raters in perception experiments that assessed the speech productions of 30 first-year college students before and after taking a pronunciation course. Our sub-group analyses revealed positive training effects for Whisper, an ASR tool, and human raters, and identified distinct human rater strategies in different assessment aspects, such as proficiency, intelligibility, accuracy, and comprehensibility, that were not observed in ASR. Despite such challenges as recognizing accented speech traits, our findings suggest that digital tools such as ASR can streamline the pronunciation assessment process. With ongoing advancements in ASR technology, its potential as not only an assessment aid but also a self-directed learning tool for pronunciation feedback merits further exploration.