Publications (10)
Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR
Qu Yang, Cakra Wardhana, Tim Ng
Code-switching (CS), alternating languages within the same utterance, poses significant challenges for automatic speech recognition (ASR) due to limited CS training data. This pape…
A Treatise On FST Lattice Based MMI Training
Adnan Haider, Tim Ng, Zhen Huang +2
Maximum mutual information (MMI) has become one of the two de facto methods for sequence-level training of speech recognition acoustic models. This paper aims to isolate, identify…
Online Automatic Speech Recognition with Listen, Attend and Spell Model
Roger Hsiao, Dogan Can, Tim Ng +2
The Listen, Attend and Spell (LAS) model and other attention-based automatic speech recognition (ASR) models have known limitations when operated in a fully online mode. In this pa…
Conformer-Based Speech Recognition On Extreme Edge-Computing Devices
Mingbin Xu, Alex Jin, Sicheng Wang +8
With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the c…
New results on pseudosquare avoidance
Tim Ng, Pascal Ochem, Narad Rampersad +1
We start by considering binary words containing the minimum possible numbers of squares and antisquares (where an antisquare is a word of the form ), and we complet…
SNDCNN: Self-normalizing deep CNNs with scaled exponential linear units for speech recognition
Zhen Huang, Tim Ng, Leo Liu +3
Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use s…