The possibility of dynamically modifying the computational load of neura...
The CHiME challenges have played a significant role in the development a...
The Streaming Unmixing and Recognition Transducer (SURT) model was propo...
Guided source separation (GSS) is a type of target-speaker extraction me...
Self-supervised learning (SSL) methods which learn representations of da...
Neural transducers have gained popularity in production ASR systems,
ach...
Self-supervised model pre-training has recently garnered significant
int...
Streaming recognition of multi-talker conversations has so far been eval...
We recently proposed DOVER-Lap, a method for combining overlap-aware spe...
This paper provides a detailed description of the Hitachi-JHU system tha...
This paper describes a method for overlap-aware speaker diarization. Giv...
Environmental noises and reverberation have a detrimental effect on the
...
Multi-speaker speech recognition of unsegmented recordings has diverse
a...
Several advances have been made recently towards handling overlapping sp...
This paper summarizes the JHU team's efforts in tracks 1 and 2 of the CH...
Deep neural network based speaker embeddings, such as x-vectors, have be...