4 papers
SegAug: CTC-Aligned Segmented Augmentation For Robust RNN-Transducer Based Speech Recognition
Khanh Le, Tuan Vu Ho, Dung Tran +1
RNN-Transducer (RNN-T) is a widely adopted architecture in speech recognition, integrating acoustic and language modeling in an end-to-end framework. However, the RNN-T predictor t…
ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription
Khanh Le, Tuan Vu Ho, Dung Tran +1
Deploying ASR models at an industrial scale poses significant challenges in hardware resource management, especially for long-form transcription tasks where audio may last for hour…
Stream-based Active Learning for Anomalous Sound Detection in Machine Condition Monitoring
Tuan Vu Ho, Kota Dohi, Yohei Kawaguchi
This paper introduces an active learning (AL) framework for anomalous sound detection (ASD) in machine condition monitoring system. Typically, ASD models are trained solely on norm…
Speak Like a Professional: Increasing Speech Intelligibility by Mimicking Professional Announcer Voice with Voice Conversion
Tuan Vu Ho, Maori Kobayashi, Masato Akagi
In most of practical scenarios, the announcement system must deliver speech messages in a noisy environment, in which the background noise cannot be cancelled out. The local noise…