The MGB challenge: Evaluating multi-genre broadcast media recognition

Abstract

This paper describes the Multi-Genre Broadcast (MGB) Challenge at ASRU 2015, an evaluation focused on speech recognition, speaker diarization, and "lightly supervised" alignment of BBC TV recordings. The challenge training data covered the whole range of seven weeks BBC TV output across four channels, resulting in about 1,600 hours of broadcast audio. In addition several hundred million words of BBC subtitle text was provided for language modelling. A novel aspect of the evaluation was the exploration of speech recognition and speaker diarization in a longitudinal setting -i.e. recognition of several episodes of the same show, and speaker diarization across these episodes, linking speakers. The longitudinal tasks also offered the opportunity for systems to make use of supplied metadata including show title, genre tag, and date/time of transmission. This paper describes the task data and evaluation process used in the MGB challenge, and summarises the results obtained.

A Contextual Study of Semantic Speech Editing in Radio Production

“…The ASR system we chose was evaluated using a large multi-genre television dataset ( Bell et al, 2015 ). It had an overall word error rate of 47%, however for news content, which is clearly spoken by a native speaker, this dropped to 16%.…”

An analysis of environment, microphone and data simulation mismatches in robust speech recognition

“…Research in this field has made great progress thanks to real speech corpora collected for various application scenarios such as voice command for cars (Hansen et al, 2001), smart homes (Ravanelli et al, 2015), or tablets (Barker et al, 2015), and automatic transcription of lectures (Lamel et al, 1994), meetings (Renals et al, 2008), conversations (Harper, 2015), dialogues (Stupakov et al, 2011), game sessions (Fox et al, 2013), or broadcast media (Bell et al, 2015). In most corpora, the training speakers differ from the test speakers.…”

Automatic speech recognition errors detection using supervised learning techniques

“…To train and evaluate the effectiveness of our proposed approach, we conducted experiments on a recent and very challenging dataset from the Multi-Genre Broadcast (MGB) Challenge [18]. The MGB data is a large broad and multigenre, spanning the whole range of TV output.…”