• The Journal of the Acoustical Society of Korea
• /
• v.18 no.1E
• /
• pp.27-31
• /
• 1999

Recent linguistic researches have brought into focus the relations between prosodic structures and syntactic, semantic or phonological structures. Most of them prove that prosodic information is available for understanding syntactic, semantic and discourse structures. But this result has not been integrated yet into recent Korean speech recognition or understanding systems. This study, as a part of integrating prosodic information into the speech recognition system, proposes an automatic detection technique of Korean accentual phrase boundaries by using one-stage DP, and the normalized pitch pattern. For making the normalized pitch pattern, this study proposes a method of modified normalization for Korean spoken language. For the experiment, this study employs 192 sentential speech data of 12 men's voice spoken in standard Korean, in which 720 accentual phrases are included, and 74.4% of the accentual phrase boundaries are correctly detected while 14.7% are the false detection rate.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.442-446
• /
• 2022

자동 음성 인식(Automatic Speech Recognition) 혹은 Speech-to-Text(STT)는 컴퓨터가 사람이 말하는 음성 언어를 텍스트 데이터로 전환하는 일련의 처리나 기술 등을 일컫는다. 음성 인식 기술이 다양한 산업 전반에 걸쳐 적용됨에 따라 높은 수준의 정확도와 더불어 다양한 분야에 적용할 수 있는 음성 인식 기술에 대한 필요성이 점차 증대되고 있다. 다만 한국어 음성 인식의 경우 기존 선행 연구에 비해 예사말/높임말의 구분이나 어미, 조사 등의 인식에 어려움이 있어 음성 인식 결과 후처리를 통한 성능 개선이 중요하다. 따라서 본 논문에서는 N-Best 음성 인식 결과가 구성되었을 때 Re-ranking을 통해 한국어 음성 인식의 성능을 개선하는 모델을 제안한다.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.1
• /
• pp.74-82
• /
• 2016

In this paper, a new automatic speech recognition (ASR) was proposed where ultrasonic doppler signals were used, instead of conventional speech signals. The proposed method has the advantages over the conventional speech/non-speech-based ASR including robustness against acoustic noises and user comfortability associated with usage of the non-contact sensor. In the method proposed herein, 40 kHz ultrasonic signal was radiated toward to the mouth and the reflected ultrasonic signals were then received. Frequency shift caused by the doppler effects was used to implement ASR. The proposed method employed multi-channel ultrasonic signals acquired from the various locations, which is different from the previous method where single channel ultrasonic signal was employed. The PCA(Principal Component Analysis) coefficients were used as the features of ASR in which hidden markov model (HMM) with left-right model was adopted. To verify the feasibility of the proposed ASR, the speech recognition experiment was carried out the 60 Korean isolated words obtained from the six speakers. Moreover, the experiment results showed that the overall word recognition rates were comparable with the conventional speech-based ASR methods and the performance of the proposed method was superior to the conventional signal channel ASR method. Especially, the average recognition rate of 90 % was maintained under the noise environments.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.4
• /
• pp.31-37
• /
• 1999

A bimodal speech recognition using visual and audio information has been proposed and researched to improve the performance of ASR(Automatic Speech Recognition) system in noisy environments. The integration method of two modalities can be usually classified into an early integration and a late integration. The early integration method includes a method using a fixed weight of lip parameters and a method using a variable weight according to speech SNR information. The 4 late integration methods are a method using audio and visual information independently, a method using speech optimal path, a method using lip optimal path and a way using speech SNR information. Among these 6 methods, the method using the fixed weight of lip parameter showed a better recognition rate.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.131-136
• /
• 2016

An appropriate evaluation on learner's pronunciation has been an important part of foreign language education. The learners should be evaluated and receive proper feedback for pronunciation improvement. Due to the cost and consistency problem of human evaluation, automatic pronunciation evaluation system has been studied. The most of the current automatic evaluation systems utilizes underlying Automatic Speech Recognition (ASR) technology. We suggest in this work to evaluate learner's pronunciation accuracy and fluency in word-level using the ASR and non-native teacher's speech model. Through the performance evaluation on our system, we confirm the overall evaluation result of pronunciation accuracy and fluency actually represents the learner's English skill level quite accurately.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.3
• /
• pp.51-56
• /
• 2000

Is this paper, we studied on the automatic speech control system in real-time windows environment using voice recognition. The applied reference pattern is the variable DMS model which is proposed to fasten execution speed and the one-stage DP algorithm using this model is used for recognition algorithm. The recognition vocabulary set is composed of control command words which are frequently used in windows environment. In this paper, an automatic speech period detection algorithm which is for on-line voice processing in windows environment is implemented. The variable DMS model which applies variable number of section in consideration of duration of the input signal is proposed. Sometimes, unnecessary recognition target word are generated. therefore model is reconstructed in on-line to handle this efficiently. The Perceptual Linear Predictive analysis method which generate feature vector from extracted feature of voice is applied. According to the experiment result, but recognition speech is fastened in the proposed model because of small loud of calculation. The multi-speaker-independent recognition rate and the multi-speaker-dependent recognition rate is 99.08% and 99.39% respectively. In the noisy environment the recognition rate is 96.25%.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.3
• /
• pp.68-72
• /
• 1999

The choice of parameters from various lip information and the robustness of extracting lip parameters play important roles in the performance of bimodal speech recognition system. In this paper, lip parameters are extracted by using an automatic extraction algorithm and inner lip parameters effect on the recognition rate more than outer lip parameters. Compared with a manual extraction algorithm, the automatic extraction method is evaluated about its robustness.

• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.123-130
• /
• 2008

Automatic lipreading is to recognize speech by observing the movement of a speaker's lips. It has received attention recently as a method of complementing performance degradation of acoustic speech recognition in acoustically noisy environments. One of the important issues in automatic lipreading is to define and extract salient features from the recorded images. In this paper, we propose a feature extraction method by using a new filtering technique for obtaining improved recognition performance. The proposed method eliminates frequency components which are too slow or too fast compared to the relevant speech information by applying a band-pass filter to the temporal trajectory of each pixel in the images containing the lip region and, then, features are extracted by principal component analysis. We show that the proposed method produces improved performance in both clean and visually noisy conditions via speaker-independent recognition experiments.

• Phonetics and Speech Sciences
• /
• v.6 no.1
• /
• pp.77-83
• /
• 2014

This paper proposes a speaker and environment clustering method in order to overcome the degradation of the speech recognition performance caused by various noise and speaker characteristics. In this paper, instead of using the distance between Gaussian mixture model (GMM) weight vectors as in the Google's approach, the distance between the adapted mean vectors based on the modified maximum a posteriori (MAP) adaptation is used as a distance measure for vector quantization (VQ) clustering. According to our experiments on the simulation data generated by adding noise to clean speech, the proposed clustering method yields error rate reduction of 10.6% compared with baseline speaker-independent (SI) model, which is slightly better performance than the Google's approach.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.75-82
• /
• 2023

Automatic speech recognition (ASR) has been revolutionized with deep learning-based approaches, among which self-supervised learning methods have proven to be particularly effective. In this study, we aim to enhance the performance of OpenAI's Whisper model, a multilingual ASR system on the Korean language. Whisper was pretrained on a large corpus (around 680,000 hours) of web speech data and has demonstrated strong recognition performance for major languages. However, it faces challenges in recognizing languages such as Korean, which is not major language while training. We address this issue by fine-tuning the Whisper model with an additional dataset comprising about 1,000 hours of Korean speech. We also compare its performance against a Transformer model that was trained from scratch using the same dataset. Our results indicate that fine-tuning the Whisper model significantly improved its Korean speech recognition capabilities in terms of character error rate (CER). Specifically, the performance improved with increasing model size. However, the Whisper model's performance on English deteriorated post fine-tuning, emphasizing the need for further research to develop robust multilingual models. Our study demonstrates the potential of utilizing a fine-tuned Whisper model for Korean ASR applications. Future work will focus on multilingual recognition and optimization for real-time inference.