• ETRI Journal
• /
• 제42권5호
• /
• pp.761-772
• /
• 2020

This paper presents an automatic proficiency assessment method for a non-native Korean read utterance using bidirectional long short-term memory (BLSTM)-based acoustic models (AMs) and speech data augmentation techniques. Specifically, the proposed method considers two scenarios, with and without prompted text. The proposed method with the prompted text performs (a) a speech feature extraction step, (b) a forced-alignment step using a native AM and non-native AM, and (c) a linear regression-based proficiency scoring step for the five proficiency scores. Meanwhile, the proposed method without the prompted text additionally performs Korean speech recognition and a subword un-segmentation for the missing text. The experimental results indicate that the proposed method with prompted text improves the performance for all scores when compared to a method employing conventional AMs. In addition, the proposed method without the prompted text has a fluency score performance comparable to that of the method with prompted text.

• 말소리와 음성과학
• /
• 제8권2호
• /
• pp.31-39
• /
• 2016

In emergency dispatching at 119 Command & Dispatch Center, some inconsistencies between the 'standard emergency aid system' and 'dispatch protocol,' which are both mandatory to follow, cause inefficiency in the dispatcher's performance. If an emergency dispatch system uses automatic speech recognition (ASR) to process the dispatcher's protocol speech during the case registration, it instantly extracts and provides the required information specified in the 'standard emergency aid system,' making the rescue command more efficient. For this purpose, we have developed a Korean large vocabulary continuous speech recognition system for 400,000 words to be used for the emergency dispatch system. The 400,000 words include vocabulary from news, SNS, blogs and emergency rescue domains. Acoustic model is constructed by using 1,300 hours of telephone call (8 kHz) speech, whereas language model is constructed by using 13 GB text corpus. From the transcribed corpus of 6,600 real telephone calls, call logs with emergency rescue command class and identified major symptom are extracted in connection with the rescue activity log and National Emergency Department Information System (NEDIS). ASR is applied to emergency dispatcher's repetition utterances about the patient information. Based on the Levenshtein distance between the ASR result and the template information, the emergency patient information is extracted. Experimental results show that 9.15% Word Error Rate of the speech recognition performance and 95.8% of emergency response detection performance are obtained for the emergency dispatch system.

• 대한음성학회지:말소리
• /
• 제49호
• /
• pp.95-105
• /
• 2004

An automatic pronunciation correction system provides learners with correction guidelines for each mispronunciation. For this purpose we develope a speech recognizer which automatically classifies pronunciation errors when Koreans speak a foreign language. In order to develope the methods for automatic assessment of pronunciation quality, we propose a language model based score as a machine score in the speech recognizer. Experimental results show that the language model based score had higher correlation with human scores than that obtained using the conventional log-likelihood based score.

• 대한음성학회지:말소리
• /
• 제49호
• /
• 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.

• 인터넷정보학회논문지
• /
• 제22권6호
• /
• pp.33-40
• /
• 2021

음성인식(ASR: Automatic Speech Recognition)은 사람의 말소리를 음성 신호로 분석하고, 문자열로 자동 변화하여 이해하는 기술이다. 초기 음성인식 기술은 하나의 단어를 인식하는 것을 시작으로 두 개 이상의 단어로 구성된 문장을 인식하는 수준까지 진화하였다. 실시간 음성 대화에 있어 높은 인식률은 자연스러운 정보전달의 편리성을 극대화하여 그 적용 범위를 확장하고 있다. 반면에, 음성인식 기술의 활발한 적용에 따라 관련된 사이버 공격과 위협에 대한 우려 역시 증가하고 있다. 기존 연구를 살펴보면, 자동화자식별(ASV: Automatic Speaker Verification) 기법의 고안과 정확성 향상 등 기술 발전 자체에 관한 연구는 활발히 이루어지고 있으나, 실생활에 적용되고 있는 음성인식 서비스의 자동화자 식별 기술에 대한 사이버 공격 및 위협에 관한 분석연구는 다양하고 깊이 있게 수행되지 않고 있다. 본 연구에서는 자동화자 식별 기술을 갖춘 AI 음성인식 서비스를 대상으로 음성 주파수와 음성속도를 조작하여 음성인증을 우회하는 사이버 공격 모델을 제안하고, 상용 스마트폰의 자동화자 식별 체계를 대상으로 실제 실험을 통해 사이버 위협을 분석한다. 이를 통해 관련 사이버 위협의 심각성을 알리고 효과적인 대응 방안에 관한 연구 관심을 높이고자 한다.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 5월 학술대회지
• /
• pp.32-35
• /
• 2003

This paper describes our recent work for developing a baseline platform for Korean spoken dialog recognition. In our work, We have collected about 65 hour speech corpus with auditory transcriptions. Linguistic information on various levels such as mophology, syntax, semantics, and discourse is attached to the speech database by using automatic or semi-automatic tools for tagging linguistic information.

• 말소리와 음성과학
• /
• 제15권3호
• /
• pp.83-88
• /
• 2023

This study investigates the fine-tuning of large-scale Automatic Speech Recognition (ASR) models, specifically OpenAI's Whisper model, for domain-specific applications using the KsponSpeech dataset. The primary research questions address the effectiveness of targeted lexical item emphasis during fine-tuning, its impact on domain-specific performance, and whether the fine-tuned model can maintain generalization capabilities across different languages and environments. Experiments were conducted using two fine-tuning datasets: Set A, a small subset emphasizing specific lexical items, and Set B, consisting of the entire KsponSpeech dataset. Results showed that fine-tuning with targeted lexical items increased recognition accuracy and improved domain-specific performance, with generalization capabilities maintained when fine-tuned with a smaller dataset. For noisier environments, a trade-off between specificity and generalization capabilities was observed. This study highlights the potential of fine-tuning using minimal domain-specific data to achieve satisfactory results, emphasizing the importance of balancing specialization and generalization for ASR models. Future research could explore different fine-tuning strategies and novel technologies such as prompting to further enhance large-scale ASR models' domain-specific performance.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 컴퓨터소사이어티 추계학술대회논문집
• /
• pp.195-198
• /
• 2003

The accuracy of automatic speech recognition system depends on the presence of background noise and speaker variability such as sex, intonation of speech, and speaking rate. Specially, the speaking rate of both inter-speaker and intra-speaker is a serious cause of mis-recognition. In this paper, we propose the compensation method of the speaking rate by the ratio of each vowel's length in a phrase. First the number of feature vectors in a phrase is estimated by the information of speaking rate. Second, the estimated number of feature vectors is assigned to each syllable of the phrase according to the ratio of its vowel length. Finally, the process of feature vector extraction is operated by the number that assigned to each syllable in the phrase. As a result the accuracy of automatic speech recognition was improved using the proposed compensation method of the speaking rate.

• 한국음향학회지
• /
• 제38권5호
• /
• pp.601-606
• /
• 2019

본 논문에서는 한국어 음성인식기 음향모델의 출력단위로 문자소를 제안한다. 제안하는 음성인식 모델은 한글을 G2P(Grapheme to Phoneme)과정 없이 초성, 중성, 종성 단위의 문자소로 분해하여 음향모델의 출력단위로 사용하며, 특별한 발음 정보를 주지 않고도 딥러닝 기반의 음향모델이 한국어 발음규정을 충분히 학습해 낼 수 있음을 보인다. 또한 기존의 음소기반 음성인식 모델과의 성능을 비교 평가하여 DB가 충분한 상황에서 문자소 기반 모델이 상대적으로 뛰어난 성능을 가진다는 것을 보인다.

• 음성과학
• /
• 제11권2호
• /
• pp.181-192
• /
• 2004

This paper presents an efficient speech interactive agent rendering smooth car navigation and Telematics services, by employing embedded automatic speech recognition (ASR), distributed speech recognition (DSR) and text-to-speech (ITS) modules, all while enabling safe driving. A speech interactive agent is essentially a conversational tool providing command and control functions to drivers such' as enabling navigation task, audio/video manipulation, and E-commerce services through natural voice/response interactions between user and interface. While the benefits of automatic speech recognition and speech synthesizer have become well known, involved hardware resources are often limited and internal communication protocols are complex to achieve real time responses. As a result, performance degradation always exists in the embedded H/W system. To implement the speech interactive agent to accommodate the demands of user commands in real time, we propose to optimize the hardware dependent architectural codes for speed-up. In particular, we propose to provide a composite solution through memory reconfiguration and efficient arithmetic operation conversion, as well as invoking an effective out-of-vocabulary rejection algorithm, all made suitable for system operation under limited resources.