Semi-supervised learning has demonstrated promising results in automatic speech
recognition (ASR) by self-training using a seed ASR model with pseudo-labels generated for …

In this work, we explore a data scheduling strategy for semi-supervised learning (SSL) for
acoustic modeling in automatic speech recognition. The conventional approach uses a seed …

In this work, we propose lattice-free MMI (LFMMI) for supervised adaptation of self-
supervised pretrained acoustic model. We pretrain a Transformer model on thousand hours …

This work investigates semi-supervised training of acoustic models (AM) with the lattice-free
maximum mutual information (LF-MMI) objective in practically relevant scenarios with a …

The state-of-the-art (SOTA) Automatic Speech Recognition (ASR) systems are mostly based
on the data-driven methods. However, low-resource languages may lack data for training …

Training deep neural network based Automatic Speech Recognition (ASR) models often
requires thousands of hours of transcribed data, limiting their use to only a few languages …

State-of-the-art acoustic models for Automatic Speech Recognition (ASR) are based on
Hidden Markov Models (HMM) and Deep Neural Networks (DNN) and often require …

論文抄録 2019 年 9 月 15 日から 19 日にかけて, オーストリア・グラーツにて ISCA
主催の国際会議 Interspeech 2019 が開催された. Interspeech は ICASSP …