Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-style queries that differ substantially from real-world search behavior, limiting their assessment of practical retrieval robustness.We present Omni-Embed-Audio (OEA), a retrievaloriented encoder leveraging multimodal LLMs with native audio understanding.To systematically evaluate robustness beyond captionstyle queries, we introduce User-Intent Queries (UIQs)-five formulations reflecting natural search behaviors: questions, commands, keyword tags, paraphrases, and exclusion-based negative queries.For negative queries, we develop a hard negative mining pipeline and propose discrimination metrics (HNSR, TFR) assessing models' ability to suppress acoustically similar distractors.Experiments on AudioCaps, Clotho, and MECAT show that OEA achieves comparable text-to-audio retrieval performance to state-of-the-art M2D-CLAP, while demonstrating clear advantages in two critical areas:(1) dominant text-to-text retrieval (+22% relative improvement), and (2) substantially superior hard negative discrimination (+4.3%pHNSR@10, +34.7% relative TFR@10), revealing that LLM backbones provide superior semantic understanding of complex queries.

To address the potential risks of AI while supporting innovation and ensuring responsible adoption, there is an urgent need for clear governance frameworks grounded in human-centric values. It is imperative that AI systems operate in ways that are transparent, trustworthy, and ethically sound. Developing truly human-centric AI goes beyond technical innovation. It requires interdisciplinary collaboration and diverse perspectives. This workshop will explore key challenges and emerging solutions in the development of human-centric AI, with a focus on explainability, trustworthiness, fairness, and privacy. We welcome both theoretical contributions and practical case studies that demonstrate how human-centered principles are realized in real-world AI systems. The official workshop webpage is available at https://xai.kaist.ac.kr/Workshop/hcai2025/, which provides comprehensive information about the program.

Due to the subjective nature of current clinical evaluation, the need for automatic severity evaluation in dysarthric speech has emerged. DNN models outperform ML models but lack user-friendly explainability. ML models offer explainable results at a feature level, but their performance is comparatively lower. Current ML models extract various features from raw waveforms to predict severity. However, existing methods do not encompass all dysarthric features used in clinical evaluation. To address this gap, we propose a feature extraction method that minimizes information loss. We introduce an ASR transcription as a novel feature extraction source. We finetune the ASR model for dysarthric speech, then use this model to transcribe dysarthric speech and extract word segment boundary information. It enables capturing finer pronunciation and broader prosodic features. These features demonstrated an improved severity prediction performance to existing features: balanced accuracy of 83.72%.

Recently, chatbot research for conversation has been actively conducted in the field of natural language processing. Among the dialogue systems, a retrieval-based system has emerged as an important one. Because, it showed better performance than the response generation models and it actually seemed applicable. The response selection task is used to develop a retrieval-based system. Thus, we did research to improve the performance of retrieval-based dialogue systems for response selection. We used Google's bidirectional encoder representations from transformers (BERT) natural-language processor with the robustly optimized BERT pre-training model (RoBERTa) as the base model to improve performance. The Recall@N of our model was improved by 1.7–4.2% using two methods: First, instead of using a simple feed-forward network at the end of the model, we employed a randomly wired neural network that contained multiple wiring paths, thus achieving better performance than that of feed-forward networks. The experimental results of this study demonstrated that feed-forward networks can be replaced by randomly wired neural networks. Second, we calculated the correlation between dialog history (i.e., context) and the last utterance of the context, reflecting this correlation as an attention network that yielded an answer prediction. Using first and second method achieved higher performance than using only the first method in dialog response selection tasks.

In this paper, we show some the implementation issues of automatic speech recognition (ASR) for portable devices. First, we propose free-running speech recognition software which does not need to push the button before saying voice command and is always running for detecting key-words under real environment. Second, we propose a method for detecting keyword and rejecting out-of-vocabularies (OOV). It consists of filler-modeling technique and utterance verification. And finally, we implement the ASR software on PDAs (Samsung SPH-M4300 and HP iPAQ-RW6100), one kind of portable devices. It works in 54.7% of real-time with the recognition accuracy of 88.3%.

In this paper, we introduce a generalized confidence score (GCS) function that enables a framework to integrate different confidence scores in speech recognition and utterance verification. A modified decoder based on the GCS is then proposed. The GCS is defined as a combination of various confidence scores obtained by exponential weighting from various confidence information sources, such as likelihood, likelihood ratio, duration, language model probabilities, etc. We also propose the use of a confidence preprocessor to transform raw scores into manageable terms for easy integration. We consider two kinds of hybrid decoders, an ordinary hybrid decoder and an extended hybrid decoder, as implementation examples based on the generalized confidence score. The ordinary hybrid decoder uses a frame-level likelihood ratio in addition to a frame-level likelihood, while a conventional decoder uses only the frame likelihood or likelihood ratio. The extended hybrid decoder uses not only the frame-level likelihood but also multilevel information such as frame-level, phone-level, and word-level confidence scores based on the likelihood ratios. Our experimental evaluation shows that the proposed hybrid decoders give better results than those obtained by the conventional decoders, especially in dealing with ill-formed utterances that contain out-of-vocabulary words and phrases.

We propose a new decoder based on a generalized confidence score. The generalized confidence score is defined as a product of confidence scores obtained from confidence information sources such as likelihood, likelihood ratio, duration, duration ratio, language model probabilities, supra-segmental information, etc. All confidence information sources are converted into confidence scores by a confidence pre-processor. We show an extended hybrid decoder as an example of the decoder based on the generalized confidence score. The extended hybrid decoder uses multi-level confidence scores such as frame-level, phone-level, and word-level likelihood ratios, while the conventional hybrid decoder uses the frame-level confidence score. The experimental result shows that the extended decoder gives a better result than the conventional hybrid decoder, particularly in dealing with out-of-vocabulary words or out-of-task sentences.

This paper describes the Korean speech corpus for train ticket reservation aid system based on speech recognition. Two sets of speech corpus were collected. One was based on human-human(H-H) dialogues and the other was based on human-computer(HC) dialogues. WOZ(Wizard of Oz) experiment was carried out to collect speech corpus based on H-C spoken dialogue. A total of 298 speaker data was collected for H-C corpus and a total of 100 speaker data was collected for H-H corpus. Since the basic unit of grammar in Korean is a morpheme, Korean-language model based on a morpheme was designed in addition to a word-based language model. Linguistic analysis results show that people respond differently when they are talking to a computer compared to when talking to a human. Also language-model analysis results reveal that a morpheme-based language model gives 50% reduction in perplexity(PP) over a word-based one.

This paper describes a Korean morphological analyzer which can be used as a part of language processor for a speech translation system.We h a v e modied the CYK algorithm so that we are able to analyze many phenomena occurring in spontaneous speech such as ellipsis, shorter words, poor and mispronounced words and so on.And we also have constructed a rule set with 112 connection rules and seven kinds of dictionaries, in which there are totally about 81,000 keywords.Currently, w e h a v e a c hieved the success rate of 93.0% with a text corpus of dialogue for hotel reservation domain.