8 papers
I-Parakeet: Integer-Only Conformer ASR on Mobile NPU
Taichi Nishimura
In this paper, we propose I-Parakeet, an integer-only implementation of NVIDIA's Parakeet-CTC (0.6B parameters) that runs on a smartphone NPU without any floating-point operator or…
Overview and Meta-Analysis of DCASE 2026 Challenge Task 6: Audio Moment Retrieval from Long Audio
Hokuto Munakata, Tatsuya Komatsu, Keisuke Imoto +3
This paper presents an overview of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2026 Challenge Task 6, Audio Moment Retrieval (AMR) from Long Audio. Given…
CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries
Hokuto Munakata, Takehiro Imamura, Taichi Nishimura +1
We introduce CASTELLA, a human-annotated audio benchmark for the task of audio moment retrieval (AMR). Although AMR has various useful potential applications, there is still no est…
DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information
Shota Nakada, Taichi Nishimura, Hokuto Munakata +2
Current audio-visual representation learning can capture rough object categories (e.g., ``animals'' and ``instruments''), but it lacks the ability to recognize fine-grained details…
Language-based Audio Moment Retrieval
Hokuto Munakata, Taichi Nishimura, Shota Nakada +1
In this paper, we propose and design a new task called audio moment retrieval (AMR). Unlike conventional language-based audio retrieval tasks that search for short audio clips from…
Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection
Taichi Nishimura, Shota Nakada, Hokuto Munakata +1
We propose Lighthouse, a user-friendly library for reproducible video moment retrieval and highlight detection (MR-HD). Although researchers proposed various MR-HD approaches, the…
On the Audio Hallucinations in Large Audio-Video Language Models
Taichi Nishimura, Shota Nakada, Masayoshi Kondo
Large audio-video language models can generate descriptions for both video and audio. However, they sometimes ignore audio content, producing audio descriptions solely reliant on v…
Vision-Language Models Learn Super Images for Efficient Partially Relevant Video Retrieval
Taichi Nishimura, Shota Nakada, Masayoshi Kondo
In this paper, we propose an efficient and high-performance method for partially relevant video retrieval, which aims to retrieve long videos that contain at least one moment relev…