6 citations · 13 across the 9 of their papers we have counts for
10 papers
Phoneme-Guided Initialization for LLM-based Speech Recognition
Ryo Magoshi, Shinsuke Sakai, Tatsuya Kawahara
Speech large language models (speech LLMs) perform well on automatic speech recognition (ASR) when sufficient paired speech-text data is available, but their performance degrades i…
Improving Zero-Shot Phonetic Classification through Language-Agnostic Articulatory Features
Ryo Magoshi, Jaeyoung Lee, Shinsuke Sakai +1
Recent Phonetic Foundation Models (PFMs) for Speech-to-IPA transcription rely on Grapheme-to-Phoneme (G2P) labels, but the phoneme labels are not necessarily phonetically faithful.…
Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer
Tomoki Honda, Shinsuke Sakai, Tatsuya Kawahara
Recently, Conformer has achieved state-of-the-art performance in many speech recognition tasks. However, the Transformer-based models show significant deterioration for long-form s…
Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM
Hayato Futami, Hirofumi Inaguma, Sei Ueno +3
Connectionist temporal classification (CTC) -based models are attractive in automatic speech recognition (ASR) because of their non-autoregressive nature. To take advantage of text…
Distilling the Knowledge of BERT for CTC-based ASR
Hayato Futami, Hirofumi Inaguma, Masato Mimura +2
Connectionist temporal classification (CTC) -based models are attractive because of their fast inference in automatic speech recognition (ASR). Language model (LM) integration appr…
ASR Rescoring and Confidence Estimation with ELECTRA
Hayato Futami, Hirofumi Inaguma, Masato Mimura +2
In automatic speech recognition (ASR) rescoring, the hypothesis with the fewest errors should be selected from the n-best list using a language model (LM). However, LMs are usually…
Distilling the Knowledge of BERT for Sequence-to-Sequence ASR
Hayato Futami, Hirofumi Inaguma, Sei Ueno +3
Attention-based sequence-to-sequence (seq2seq) models have achieved promising results in automatic speech recognition (ASR). However, as these models decode in a left-to-right way,…
Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition
Kohei Matsuura, Masato Mimura, Shinsuke Sakai +1
It is important to transcribe and archive speech data of endangered languages for preserving heritages of verbal culture and automatic speech recognition (ASR) is a powerful tool t…
Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language
Kohei Matsuura, Sei Ueno, Masato Mimura +2
Ainu is an unwritten language that has been spoken by Ainu people who are one of the ethnic groups in Japan. It is recognized as critically endangered by UNESCO and archiving and d…
Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR
Hirofumi Inaguma, Masato Mimura, Shinsuke Sakai +1
Acoustic-to-word (A2W) end-to-end automatic speech recognition (ASR) systems have attracted attention because of an extremely simplified architecture and fast decoding. To alleviat…