5 papers · 1 filter
Residual Language Model for End-to-end Speech Recognition
Emiru Tsunoo, Yosuke Kashiwagi, Chaitanya Narisetty +1
End-to-end automatic speech recognition suffers from adaptation to unknown target domain speech despite being trained with a large amount of paired audio--text data. Recent studies…
Joint Speech Recognition and Audio Captioning
Chaitanya Narisetty, Emiru Tsunoo, Xuankai Chang +3
Speech samples recorded in both indoor and outdoor environments are often contaminated with secondary audio sources. Most end-to-end monaural speech recognition systems either remo…
Run-and-back stitch search: novel block synchronous decoding for streaming encoder-decoder ASR
Emiru Tsunoo, Chaitanya Narisetty, Michael Hentschel +2
A streaming style inference of encoder-decoder automatic speech recognition (ASR) system is important for reducing latency, which is essential for interactive use cases. To this en…
Data Augmentation Methods for End-to-end Speech Recognition on Distant-Talk Scenarios
Emiru Tsunoo, Kentaro Shibata, Chaitanya Narisetty +2
Although end-to-end automatic speech recognition (E2E ASR) has achieved great performance in tasks that have numerous paired data, it is still challenging to make E2E ASR robust ag…
Modelling of Sound Events with Hidden Imbalances Based on Clustering and Separate Sub-Dictionary Learning
Chaitanya Narisetty, Tatsuya Komatsu, Reishi Kondo
This paper proposes an effective modelling of sound event spectra with a hidden data-size-imbalance, for improved Acoustic Event Detection (AED). The proposed method models each ev…