arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1312.6849cs.CLcs.CVcs.LG
收藏

无信息丢失的语音识别前端

Speech Recognition Front End Without Information Loss

King’s College London(伦敦国王学院)

Matthew Ager, Zoran Cvetkovic, Peter Sollich

摘要:

为了提高自动语音识别对加性噪声的鲁棒性,研究了声学波形或其线性变换的高维空间中的语音表示和建模。这种方法背后的动机是双重的:(i)在提取低维特征的过程中通常被去除的声波波形中的信息可能借助于类似于信道编码的结构化冗余来帮助鲁棒识别,(ii)线性特征域允许精确的噪声自适应,与涉及非线性处理的表示相反,非线性处理使得噪声自适应具有挑战性。因此,我们开发了一个生成框架的音素建模在高维线性特征域,并使用它在音素分类和识别任务。实验结果表明,在低于18 dB的信噪比下,该框架的分类和识别性能优于类似的PLP和MFCC分类器。在所有噪声水平上,在似然水平上的高维和MFCC特征的组合一致地比单独表示中的任一个表现得更好。

英文摘要:

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The motivation behind this approach is twofold: (i) the information in acoustic waveforms that is usually removed in the process of extracting low-dimensional features might aid robust recognition by virtue of structured redundancy analogous to channel coding, (ii) linear feature domains allow for exact noise adaptation, as opposed to representations that involve non-linear processing which makes noise adaptation challenging. Thus, we develop a generative framework for phoneme modelling in high-dimensional linear feature domains, and use it in phoneme classification and recognition tasks. Results show that classification and recognition in this framework perform better than analogous PLP and MFCC classifiers below 18 dB SNR. A combination of the high-dimensional and MFCC features at the likelihood level performs uniformly better than either of the individual representations across all noise levels.

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。

↑