Related papers: Integrating HMM-Based Speech Recognition With Dire…
A bi-directional Korean/English dialog translation system is designed and implemented using the memory-based translation technique. The system KEMDT (Korean/English Memory-based Dialog Translation system) can perform Korean to English, and…
The Korean wave, which denotes the global popularity of South Korea's cultural economy, contributes to the increasing demand for the Korean language. However, as there does not exist any application for foreigners to learn Korean, this…
Self-supervised learning (SSL) approaches such as wav2vec 2.0 and HuBERT models have shown promising results in various downstream tasks in the speech community. In particular, speech representations learned by SSL models have been shown to…
Speech Emotion Recognition (SER) is of great importance in Human-Computer Interaction (HCI), as it provides a deeper understanding of the situation and results in better interaction. In recent years, various machine learning and Deep…
Running automatic speech recognition (ASR) on edge devices is non-trivial due to resource constraints, especially in scenarios that require supporting multiple languages. We propose a new approach to enable multilingual speech recognition…
The deployment of large language models (LLMs) presents significant challenges due to their enormous memory footprints, low arithmetic intensity, and stringent latency requirements, particularly during the autoregressive decoding stage.…
Automatic Speech Recognition (ASR) models demonstrate outstanding performance on high-resource languages but face significant challenges when applied to low-resource languages due to limited training data and insufficient cross-lingual…
Producing a large annotated speech corpus for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced, but collecting a relatively big unlabeled data set for such languages is more…
Multilingual automatic speech recognition (ASR) systems have garnered attention for their potential to extend language coverage globally. While self-supervised learning (SSL) models, like MMS, have demonstrated their effectiveness in…
Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically…
Translating human intent into robot commands is crucial for the future of service robots in an aging society. Existing Human-Robot Interaction (HRI) systems relying on gestures or verbal commands are impractical for the elderly due to…
Sign language recognition (SLR) facilitates communication between deaf and hearing individuals. Deep learning is widely used to develop SLR-based systems; however, it is computationally intensive and requires substantial computational…
Speech discrete representation has proven effective in various downstream applications due to its superior compression rate of the waveform, fast convergence during training, and compatibility with other modalities. Discrete units extracted…
Self-supervised learning representation (SSLR) has demonstrated its significant effectiveness in automatic speech recognition (ASR), mainly with clean speech. Recent work pointed out the strength of integrating SSLR with single-channel…
The performance of automatic speech recognition (ASR) models can be greatly improved by proper beam-search decoding with external language model (LM). There has been an increasing interest in Korean speech recognition, but not many studies…
Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…
This research explores using lightweight deep neural network architectures to enable the humanoid robot Pepper to understand American Sign Language (ASL) and facilitate non-verbal human-robot interaction. First, we introduce a lightweight…
Speaker identification is a powerful, non-invasive and in-expensive biometric technique. The recognition accuracy, however, deteriorates when noise levels affect a specific band of frequency. In this paper, we present a sub-band based…
In this study, we introduce KOPL, a novel framework for handling Korean OOV words with Phoneme representation Learning. Our work is based on the linguistic property of Korean as a phonemic script, the high correlation between phonemes and…
Hate speech detection is a challenging natural language processing task that requires capturing linguistic and contextual nuances. Pre-trained language models (PLMs) offer rich semantic representations of text that can improve this task.…