CASIA-CASSIL is a large-scale corpus base of Chinese human-human naturally-occurring telephone conversations in restricted domains. The first edition consists of 792 90-second con...
Abstract--In this paper, we report on the performance of automatic speech recognition (ASR) systems on voicemail transcription. Voicemail is spontaneous telephone speech recorded o...
Mukund Padmanabhan, George Saon, Jing Huang, Brian...
This paper proposes a platform that aims to support the whole process and facilitate archiving tasks at museums and galleries. When we try to preserve tacit knowledge or skills of ...
Current state-of?the-art spoken dialog systems are aimed at handling telephone calls to automate incoming caller requests. In this paper we explore a scenario which is symmetric t...
The regular occurrence of disfluencies is a distinguishing characteristic of spontaneous speech. Detecting and removing such disfluencies can substantially improve the usefulness ...