We present a study on purely data-based recognition of animal sounds, performing evaluation on a real-world database obtained from the Humboldt-University Animal Sound Archive. As...
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...
Practical supervised learning scenarios involving subjectively evaluated data have multiple evaluators, each giving their noisy version of the hidden ground truth. Majority logic ...
In an attempt to improve models of human perception, the recognition of phonemes in nonsense utterances was predicted with automatic speech recognition (ASR) in order to analyze i...
This paper describes the evaluation methodology used to evaluate the TC-STAR speech-to-speech translation (SST) system and their results from the third year of the project. It fol...