• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.284-290
• /
• 2024

Speech emotion recognition (SER) is a technique that is used to analyze the speaker's voice patterns, including vibration, intensity, and tone, to determine their emotional state. There has been an increase in interest in artificial intelligence (AI) techniques, which are now widely used in medicine, education, industry, and the military. Nevertheless, existing researchers have attained impressive results by utilizing acted-out speech from skilled actors in a controlled environment for various scenarios. In particular, there is a mismatch between acted and spontaneous speech since acted speech includes more explicit emotional expressions than spontaneous speech. For this reason, spontaneous speech-emotion recognition remains a challenging task. This paper aims to conduct emotion recognition and improve performance using spontaneous speech data. To this end, we implement deep learning-based speech emotion recognition using the VGG (Visual Geometry Group) after converting 1-dimensional audio signals into a 2-dimensional spectrogram image. The experimental evaluations are performed on the Korean spontaneous emotional speech database from AI-Hub, consisting of 7 emotions, i.e., joy, love, anger, fear, sadness, surprise, and neutral. As a result, we achieved an average accuracy of 83.5% and 73.0% for adults and young people using a time-frequency 2-dimension spectrogram, respectively. In conclusion, our findings demonstrated that the suggested framework outperformed current state-of-the-art techniques for spontaneous speech and showed a promising performance despite the difficulty in quantifying spontaneous speech emotional expression.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.2E
• /
• pp.38-46
• /
• 1998

In this paper, we propose a remote speech input device, a new method of user-friendly speech input in spontaneous speech recognition system. We focus the user friendliness on hands-free and microphone independence in speech recognition applications. Our method adopts two algorithms, the automatic speech detection and the microphone array delay-and-sum beamforming (DSBF)-based speech enhancement. The automatic speech detection algorithm is composed of two stages; the detection of speech and nonspeech using the pitch information for the detected speech portion candidate. The DSBF algorithm adopts the time domain cross-correlation method as its time delay estimation. In the performance evaluation, the speech detection algorithm shows within-200 ms start point accuracy of 93%, 99% under 15dB, 20dB, and 25dB signal-to-noise ratio (SNR) environments, respectively and those for the end point are 72%, 89%, and 93% for the corresponding environments, respectively. The classification of speech and nonspeech for the start point detected region of input signal is performed by the pitch information-base method. The percentages of correct classification for speech and nonspeech input are 99% and 90%, respectively. The eight microphone array-based speech enhancement using the DSBF algorithm shows the maximum SNR gaing of 6dB over a single microphone and the error reductin of more than 15% in the spontaneous speech recognition domain.

• 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.

• MALSORI
• /
• no.46
• /
• pp.117-126
• /
• 2003

This paper presents our language model adaptation for Korean spontaneous speech recognition. Korean spontaneous speech is observed various characteristics of content and style such as filled pauses, word omission, and contraction as compared with the written text corpus. Our approaches focus on improving the estimation of domain-dependent n-gram models by relevance weighting out-of-domain text data, where style is represented by n-gram based tf/sup */idf similarity. In addition to relevance weighting, we use disfluencies as Predictor to the neighboring words. The best result reduces 9.7% word error rate relatively and shows that n-gram based relevance weighting reflects style difference greatly and disfluencies are good predictor also.

• Phonetics and Speech Sciences
• /
• v.11 no.3
• /
• pp.39-47
• /
• 2019

We propose a method to improve the performance of spontaneous speech recognizers by extending their phone set using speech data. In the proposed method, we first extract variable-length phoneme-level segments from broadcast speech signals, and convert them to fixed-length latent vectors using an long short-term memory (LSTM) classifier. We then cluster acoustically similar latent vectors and build a new phone set by choosing the number of clusters with the lowest Davies-Bouldin index. We also update the lexicon of the speech recognizer by choosing the pronunciation sequence of each word with the highest conditional probability. In order to analyze the acoustic characteristics of the new phone set, we visualize its spectral patterns and segment duration. Through speech recognition experiments using a larger training data set than our own previous work, we confirm that the new phone set yields better performance than the conventional phoneme-based and grapheme-based units in both spontaneous speech recognition and read speech recognition.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.705-708
• /
• 2009

This research describes a neural network-based phoneme segmenter for recognizing spontaneous speech. The input of the phoneme segmenter for spontaneous speech is 16th order mel-scaled FFT, normalized frame energy, ratio of energy among 0~3[KHz] band and more than 3[KHz] band. All the features are differences of two consecutive 10 [msec] frame. The main body of the segmenter is single-hidden layer MLP(Multi-Layer Perceptron) with 72 inputs, 20 hidden nodes, and one output node. The segmentation accuracy is 78% with 7.8% insertion.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2E
• /
• pp.51-55
• /
• 2004

In this paper, we propose a style-specific language model adaptation scheme using n-gram based tf*idf similarity for Korean spontaneous speech recognition. Korean spontaneous speech shows especially different style-specific characteristics such as filled pauses, word omission, and contraction, which are related to function words and depend on preceding or following words. To reflect these style-specific characteristics and overcome insufficient data for training language model, we estimate in-domain dependent n-gram model by relevance weighting of out-of-domain text data according to their n-. gram based tf*idf similarity, in which in-domain language model include disfluency model. Recognition results show that n-gram based tf*idf similarity weighting effectively reflects style difference.

• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.9-22
• /
• 2017

The purpose of this paper is to report the whole process of developing Korean Standard Speech Database (KSS DB). This project is supported by SPO (Supreme Prosecutors' Office) research grant for three years from 2014 to 2016. KSS DB is designed to provide speech data for acoustic-phonetic and phonological studies and speaker recognition system. For the samples to represent the spoken Korean, sociolinguistic factors, such as region (9 regional dialects), age (5 age groups over 20) and gender (male and female) were considered. The goal of the project is to collect over 3,000 male and female speakers of nine regional dialects and five age groups employing direct and indirect methods. Speech samples of 3,191 speakers (2,829 speakers and 362 speakers using direct and indirect methods, respectively) are collected and databased. KSS DB designs to collect read and spontaneous speech samples from each speaker carrying out 5 speech tasks: three (pseudo-)spontaneous speech tasks (producing prolonged simple vowels, 28 blanked sentences and spontaneous talk) and two read speech tasks (reading 55 phonetically and phonologically rich sentences and reading three short passages). KSS DB includes a 16-bit, 44.1kHz speech waveform file and a orthographic file for each speech task.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.330-338
• /
• 2002

Spontaneous speech is ungrammatical as well as serious phonological variations, which make recognition extremely difficult, compared with read speech. In this paper, for conversational speech recognition, we analyze the transcriptions of the real conversational speech, and then classify the characteristics of conversational speech in the speech recognition aspect. Reflecting these features, we obtain the baseline system for conversational speech recognition. The classification consists of long duration of silence, disfluencies and phonological variations; each of them is classified with similar features. To deal with these characteristics, first, we update silence model and append a filled pause model, a garbage model; second, we append multiple phonetic transcriptions to lexicon for most frequent phonological variations. In our experiments, our baseline morpheme error rate (WER) is 31.65%; we obtain MER reductions such as 2.08% for silence and garbage model, 0.73% for filled pause model, and 0.73% for phonological variations. Finally, we obtain 27.92% MER for conversational speech recognition, which will be used as a baseline for further study.

• ETRI Journal
• /
• v.46 no.1
• /
• 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.