Many real-life applications of automatic speech recognition (ASR) requir...
MeetEval is an open-source toolkit to evaluate all kinds of meeting
tran...
Multi-speaker automatic speech recognition (ASR) is crucial for many
rea...
We introduce a monaural neural speaker embeddings extractor that compute...
Since diarization and source separation of meeting data are closely rela...
We present a general framework to compute the word error rate (WER) of A...
This paper proposes reverberation as supervision (RAS), a novel unsuperv...
Recent speaker diarization studies showed that integration of end-to-end...
We propose a system that transcribes the conversation of a typical meeti...
Spatial mixture model (SMM) supported acoustic beamforming has been
exte...
Impressive progress in neural network-based single-channel speech source...
Many state-of-the-art neural network-based source separation systems use...
Automatic transcription of meetings requires handling of overlapped spee...
Permutation invariant training (PIT) is a widely used training criterion...
Unsupervised blind source separation methods do not require a training p...
Recently, the end-to-end approach has been successfully applied to
multi...
Time-domain training criteria have proven to be very effective for the
s...
We present ESPnet-SE, which is designed for the quick development of spe...
Most approaches to multi-talker overlapped speech separation and recogni...
This paper proposes methods that can optimize a Convolutional BeamFormer...
The rising interest in single-channel multi-speaker speech separation sp...
The rising interest in single-channel multi-speaker speech separation sp...
In recent years time domain speech separation has excelled over frequenc...
We present a multi-channel database of overlapping speech for training,
...
We previously proposed an optimal (in the maximum likelihood sense)
conv...
Despite the strong modeling power of neural network acoustic models, spe...
In this paper, we present Hitachi and Paderborn University's joint effor...