Teach An All-rounder With Experts In Different Domains

Abstract

In many automatic speech recognition (ASR) tasks, an ideal model has to be applicable over multiple domains. In this paper, we propose to teach an all-rounder with experts in different domains. Concretely, we build a multi-domain acoustic model by applying the teacher-student training framework. First, for each domain, a teacher model (domain-dependent model) is trained by fine-tuning a multi-condition model with domain-specific subset. Then all these teacher models are used to teach one single student model simultaneously. We perform experiments on two predefined domain setups. One is domains with different speaking styles, the other is nearfield, far-field and far-field with noise. Moreover, two types of models are examined: deep feedforward sequential memory network (DFSMN) and long short term memory (LSTM). Experimental results show that the model trained with this framework outperforms not only multi-condition model but also domain-dependent model. Specially, our training method p

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyyou2019teach

Related papers

• Large-scale Domain Adaptation Via Teacher-student Learning (2017)13.93
• Advancing Multi-accented LSTM-CTC Speech Recognition Using A Domain Specific Student-teacher Learning Paradigm (2018)7.81
• Fully Learnable Front-end For Multi-channel Acoustic Modeling Using Semi-supervised Learning (2020)2.26
• Adversarial Training For Multi-domain Speaker Recognition (2020)6.77
• Frequency Domain Multi-channel Acoustic Modeling For Distant Speech Recognition (2019)9.92
• Toward Domain-invariant Speech Recognition Via Large Scale Training (2018)13.39
• Investigating Self-supervised, Weakly Supervised And Fully Supervised Training Approaches For Multi-domain Automatic Speech Recognition: A Study On Bangladeshi Bangla (2022)0.00
• Multi-domain Spoken Language Understanding Using Domain- And Task-aware Parameterization (2020)3.58