2015年谢菲尔德多类型广播媒体转录系统
The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media
摘要:
我们描述了谢菲尔德大学系统参与2015年多流派广播(MGB)的挑战任务转录多流派广播节目。转录是MGB挑战中提出的四项任务之一,目的是推进自动语音识别、说话人日记和广播媒体字幕自动对齐的最新技术水平。在这项工作中,四个主题进行了研究:数据选择技术与不可靠的数据,自动语音分割的广播媒体节目,声学建模和适应在高度可变的环境中,和语言建模的多流派节目的培训。最终的系统在多个通道中操作,使用初始的非自适应解码阶段来细化分割,然后是三个自适应通道:混合DNN通道,其输入特征通过基于扬声器的倒谱归一化进行归一化,另一个混合阶段,其输入特征通过扬声器特征MLLR变换进行归一化,最后是基于降噪的串联阶段,其具有噪声和扬声器因子分解。这三个系统输出的组合提供了一个最终的出错率为27.5%的官方开发集,包括47个多类型的节目。
英文摘要:
We describe the University of Sheffield system for participation in the 2015 Multi-Genre Broadcast (MGB) challenge task of transcribing multi-genre broadcast shows. Transcription was one of four tasks proposed in the MGB challenge, with the aim of advancing the state of the art of automatic speech recognition, speaker diarisation and automatic alignment of subtitles for broadcast media. Four topics are investigated in this work: Data selection techniques for training with unreliable data, automatic speech segmentation of broadcast media shows, acoustic modelling and adaptation in highly variable environments, and language modelling of multi-genre shows. The final system operates in multiple passes, using an initial unadapted decoding stage to refine segmentation, followed by three adapted passes: a hybrid DNN pass with input features normalised by speaker-based cepstral normalisation, another hybrid stage with input features normalised by speaker feature-MLLR transformations, and finally a bottleneck-based tandem stage with noise and speaker factorisation. The combination of these three system outputs provides a final error rate of 27.5% on the official development set, consisting of 47 multi-genre shows.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。