31 citations · 67 across the 31 of their papers we have counts for
10 papers · 1 filter
Progressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training
Rehan Ahmad, Muhammad Umar Farooq, Thomas Hain
In Automatic Speech Recognition (ASR), teacher-student (T/S) training has shown to perform well for domain adaptation with small amount of training data. However, adaption without…
Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation
Rehan Ahmad, Md Asif Jalal, Muhammad Umar Farooq +2
Knowledge distillation has widely been used for model compression and domain adaptation for speech applications. In the presence of multiple teachers, knowledge can easily be trans…
Unsupervised data selection for Speech Recognition with contrastive loss ratios
Chanho Park, Rehan Ahmad, Thomas Hain
This paper proposes an unsupervised data selection method by using a submodular function based on contrastive loss ratios of target and training data sets. A model using a contrast…
Efficient Non-Autoregressive GAN Voice Conversion using VQWav2vec Features and Dynamic Convolution
Mingjie Chen, Yanghao Zhou, Heyan Huang +1
It was shown recently that a combination of ASR and TTS models yield highly competitive performance on standard voice conversion tasks such as the Voice Conversion Challenge 2020 (…
Improving Audio Anomalies Recognition Using Temporal Convolutional Attention Network
Qiang Huang, Thomas Hain
Anomalous audio in speech recordings is often caused by speaker voice distortion, external noise, or even electric interferences. These obstacles have become a serious problem in s…
Unsupervised Acoustic Unit Representation Learning for Voice Conversion using WaveNet Auto-encoders
Mingjie Chen, Thomas Hain
Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work…