The development of a speech translation (ST) system is costly, largely because it is expensive to collect parallel data. A new language pair is typically only considered in the af...
A novel Statistical Approach for F0 Estimation, SAFE, is proposed to improve the accuracy of F0 tracking under both clean and additive noise conditions. Prominent Signal-to-Noise ...
In missing feature based automatic speech recognition (ASR), the role of the spectro-temporal mask in providing an accurate description of the relationship between target speech a...
We extend our earlier work on deep-structured conditional random field (DCRF) and develop deep-structured hidden conditional random field (DHCRF). We investigate the use of this n...
This paper describes improvements in a search error risk minimization approach to fast beam search for speech recognition. In our previous work, we proposed this approach to reduc...