• IEIE Transactions on Smart Processing and Computing
• /
• 제3권5호
• /
• pp.259-266
• /
• 2014

In this paper, we propose a novel technique for noise robust automatic speech recognition (ASR). The development of ASR techniques has made it possible to recognize isolated words with a near perfect word recognition rate. However, in a highly noisy environment, a distinct mismatch between the trained speech and the test data results in a significantly degraded word recognition rate (WRA). Unlike conventional ASR systems employing Mel-frequency cepstral coefficients (MFCCs) and a hidden Markov model (HMM), this study employ histogram of oriented gradient (HOG) features and a Support Vector Machine (SVM) to ASR tasks to overcome this problem. Our proposed ASR system is less vulnerable to external interference noise, and achieves a higher WRA compared to a conventional ASR system equipped with MFCCs and an HMM. The performance of our proposed ASR system was evaluated using a phonetically balanced word (PBW) set mixed with artificially added noise.

• ETRI Journal
• /
• 제46권1호
• /
• pp.48-58
• /
• 2024

This paper presents the development of language tutoring systems for nonnative speakers by leveraging advanced end-to-end automatic speech recognition (ASR) and proficiency evaluation. Given the frequent errors in non-native speech, high-performance spontaneous speech recognition must be applied. Our systems accurately evaluate pronunciation and speaking fluency and provide feedback on errors by relying on precise transcriptions. End-to-end ASR is implemented and enhanced by using diverse non-native speaker speech data for model training. For performance enhancement, we combine semisupervised and transfer learning techniques using labeled and unlabeled speech data. Automatic proficiency evaluation is performed by a model trained to maximize the statistical correlation between the fluency score manually determined by a human expert and a calculated fluency score. We developed an English tutoring system for Korean elementary students called EBS AI Peng-Talk and a Korean tutoring system for foreigners called KSI Korean AI Tutor. Both systems were deployed by South Korean government agencies.

• 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.

• ETRI Journal
• /
• 제46권1호
• /
• 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.

• 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 2007년도 하계종합학술대회 논문집
• /
• pp.303-304
• /
• 2007

In this paper, we implement an automatic distance speech recognition system for voiced-enabled services. We first construct a baseline automatic speech recognition (ASR) system, where acoustic models are trained from speech utterances spoken by using a cross-talking microphone. In order to improve the performance of the baseline ASR using distance speech, the acoustic models are adapted to adjust the spectral characteristics of speech according to different microphones and the environmental mismatches between cross-talking and distance speech. Next we develop a voice activity detection algorithm for distance speech. We compare the performance of the base-line system and the developed ASR system on a task of PBW (Phonetically Balanced Word) 452. As a result it is shown that the developed ASR system provides the average word error rate (WER) reduction of 30.6 % compared to the baseline ASR system.

• 말소리와 음성과학
• /
• 제10권1호
• /
• pp.33-38
• /
• 2018

Although deep neural network-based acoustic models have greatly improved the performance of automatic speech recognition (ASR), reverberation still degrades the performance of distant speech recognition in indoor environments. In this paper, we adopt the DenseNet, which has shown great performance results in image classification tasks, to improve the performance of reverberant speech recognition. The DenseNet enables the deep convolutional neural network (CNN) to be effectively trained by concatenating feature maps in each convolutional layer. In addition, we extend the concept of multi-resolution CNN to multi-resolution DenseNet for robust speech recognition in reverberant environments. We evaluate the performance of reverberant speech recognition on the single-channel ASR task in reverberant voice enhancement and recognition benchmark (REVERB) challenge 2014. According to the experimental results, the DenseNet-based acoustic models show better performance than do the conventional CNN-based ones, and the multi-resolution DenseNet provides additional performance improvement.

• 대한음성학회지:말소리
• /
• 제43호
• /
• pp.45-55
• /
• 2002

High reliability of automatic speaker recognition regardless of voice conditions is necessary for forensic application. Audio recordings in real cases are not consistent in voice conditions, such as duration, time interval of recording, given text or conversational speech, transmission channel, etc. In this study the variation of verification error rate of ASR system with the voice conditions was investigated. As a result in order to decrease both false rejection rate and false acception rate, the various voices should be used for training and the duration of train voices should be longer than the test voices.

• 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.

• 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.