As for other forms of AI, speech recognition has recently been examined ...
We present an approach to reduce the performance disparity between geogr...
We present a streaming, Transformer-based end-to-end automatic speech
re...
In this paper, we propose an approach to quantitatively analyze impacts ...
Dynamic Linear Models (DLMs) are commonly employed for time series analy...
We propose a simple yet effective method to compress an RNN-Transducer
(...
Transformers are powerful neural architectures that allow integrating
di...
Acoustic models in real-time speech recognition systems typically stack
...