...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on audio, speech and language processing >Combining Spectral Representations for Large-Vocabulary Continuous Speech Recognition
【24h】

Combining Spectral Representations for Large-Vocabulary Continuous Speech Recognition

机译：结合频谱表示法进行大词汇量连续语音识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we investigate the combination of complementary acoustic feature streams in large-vocabulary continuous speech recognition (LVCSR). We have explored the use of acoustic features obtained using a pitch-synchronous analysis, Straight, in combination with conventional features such as Mel frequency cepstral coefficients. Pitch-synchronous acoustic features are of particular interest when used with vocal tract length normalization (VTLN) which is known to be affected by the fundamental frequency. We have combined these spectral representations directly at the acoustic feature level using heteroscedastic linear discriminant analysis (HLDA) and at the system level using ROVER. We evaluated this approach on three LVCSR tasks: dictated newspaper text (WSJCAM0), conversational telephone speech (CTS), and multiparty meeting transcription. The CTS and meeting transcription experiments were both evaluated using standard NIST test sets and evaluation protocols. Our results indicate that combining conventional and pitch-synchronous acoustic feature sets using HLDA results in a consistent, significant decrease in word error rate across all three tasks. Combining at the system level using ROVER resulted in a further significant decrease in word error rate.
机译：在本文中，我们研究了大词汇量连续语音识别（LVCSR）中互补声学特征流的组合。我们已经探索了通过音高同步分析Straight获得的声学特征与常规特征（例如梅尔频率倒谱系数）的结合使用。与已知受基频影响的声道长度归一化（VTLN）一起使用时，音高同步声学特征特别受关注。我们已经使用异方差线性判别分析（HLDA）直接在声学特征级别上组合了这些频谱表示，并使用ROVER在系统级别上组合了这些频谱表示。我们在三个LVCSR任务上评估了该方法：口述报纸文本（WSJCAM0），对话电话语音（CTS）和多方会议抄录。 CTS和会议转录实验均使用标准NIST测试集和评估协议进行评估。我们的结果表明，使用HLDA组合常规和音高同步声学特征集会在所有三个任务中导致字错误率的持续显着降低。使用ROVER在系统级别进行组合会进一步显着降低单词错误率。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号