3.3k citations
- NTT Basic Research LaboratoriesJP437 papers
- The University of TokyoJP123 papers
- Japan Science and Technology AgencyJP95 papers
- National Institute of InformaticsJP60 papers
- The University of OsakaJP52 papers
- Tokyo Institute of TechnologyJP47 papers
- Kyoto UniversityJP39 papers
- Waseda UniversityJP28 papers
- Delft University of TechnologyNL25 papers
- Nagoya UniversityJP25 papers
- Stanford UniversityUS24 papers
- Tohoku UniversityJP24 papers
4 papers · 2 filters
On Word Error Rate Definitions and their Efficient Computation for Multi-Speaker Speech Recognition Systems
Thilo von Neumann, Christoph Boeddeker, Keisuke Kinoshita +2
We propose a general framework to compute the word error rate (WER) of ASR systems that process recordings containing multiple speakers at their input and that produce multiple out…
ConceptBeam: Concept Driven Target Speech Extraction
Yasunori Ohishi, Marc Delcroix, Tsubasa Ochiai +6
We propose a novel framework for target speech extraction based on semantic information, called ConceptBeam. Target speech extraction means extracting the speech of a target speake…
BYOL for Audio: Exploring Pre-trained General-purpose Audio Representations
Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi +2
Pre-trained models are essential as feature extractors in modern machine learning systems in various domains. In this study, we hypothesize that representations effective for gener…
Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition
Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix +3
The combination of a deep neural network (DNN) -based speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end is a widely used approach to implement ov…