research
∙
06/15/2023
Competitive and Resource Efficient Factored Hybrid HMM Systems are Simpler Than You Think
Building competitive hybrid hidden Markov model (HMM) systems for automa...
share
research
∙
01/11/2023
Improving And Analyzing Neural Speaker Embeddings for ASR
Neural speaker embeddings encode the speaker's speech characteristics th...
research
∙
10/26/2022
Efficient Use of Large Pre-Trained Models for Low Resource ASR
Automatic speech recognition (ASR) has been established as a well-perfor...
research
∙
10/24/2022
Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speech
Language barriers present a great challenge in our increasingly connecte...
research
∙
06/26/2022
Improving the Training Recipe for a Robust Conformer-based Hybrid Model
Speaker adaptation is important to build robust automatic speech recogni...
research
∙
11/05/2021
Conformer-based Hybrid ASR System for Switchboard Dataset
The recently proposed conformer architecture has been successfully used ...
research
∙
04/09/2021
Feature Replacement and Combination for Hybrid ASR Systems
Acoustic modeling of raw waveform and learning feature extractors as par...
research
∙
05/08/2019