Research on speech processing has traditionally considered the task of designing hand-
engineered acoustic features (feature engineering) as a separate distinct problem from the …

This paper introduces a new open source platform for end-to-end speech processing named
ESPnet. ESPnet mainly focuses on end-to-end automatic speech recognition (ASR), and …

Speech data is crucially important for speech recognition research. There are quite some
speech databases that can be purchased at prices that are reasonable for most research …

In our Big Data era, data is being generated, collected and analyzed at an unprecedented
scale, and data-driven decision making is sweeping through all aspects of society. Recent …

This paper presents BUT ReverbDB-a dataset of real room impulse responses (RIR),
background noises, and retransmitted speech data. The retransmitted data include …

Several advances have been made recently towards handling overlapping speech for
speaker diarization. Since speech and natural language tasks often benefit from ensemble …

The CALO Meeting Assistant (MA) provides for distributed meeting capture, annotation,
automatic transcription and semantic analysis of multiparty meetings, and is part of the larger …

This paper proposes a unified architecture for end-to-end automatic speech recognition
(ASR) to encompass microphone-array signal processing such as a state-of-the-art neural …

The AMI and AMIDA projects are concerned with the recognition and interpretation of
multiparty meetings. Within these projects we have: developed an infrastructure for …

The field of speech recognition is in the midst of a paradigm shift: end-to-end neural
networks are challenging the dominance of hidden Markov models as a core technology …