Large-vocabulary continuous speech recognition on spontaneous speech task

自发语音任务的大词汇量连续语音识别

• 批准号: 18500126
• 负责人: KOHDA Masaki
• 金额: $ 1.22万
• 依托单位: Yamagata University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2006
• 资助国家: 日本
• 起止时间: 2006 至 2007
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-18500126/
• 关键词: Corpus of Spontaneous Japanese; Speech recognition; Acoustic model; Language model; Unsupervised adaptation; System integration; Robust speech recognition; 混合連続分布HMM; 離散混合分布HMM

1. Large-vocabulary continuous speech recognition on spontaneous speech taskIn large-vocabulary continuous speech recognition, we investigate several methods of unsupervised adaptation of both acoustic and language models and evaluate the methods on the Corpus of Spontaneous Japanese (CSJ). The LVCSR system has full-covariance matrices as the acoustic model. The results of recognition experiments showed the decrease in word error rate (WER) from 19.17% without adaptation to 14.73% with unsupervised adaptation, moreover to 14.47% with unsupervised adaptation by weighting the adaptation data on the basis of a part of speech. Also, we compared the performance between continuous-mixture FRAM (CHMM) system and discrete-mixture HMM (DMHMM) system on the CSJ. As a result, DMHMM system provided almost the same performance as the CHMM system and WER of 19.73% had been obtained with 6000-state 24-mixture DMHMMs, though it has been generally believed that the recognition error rates of DMHMM were … More much higher than those of CHMM until now.2. Robust speech recognition using discrete-mixture HMMsWe introduce a new method of robust speech recognition under noisy conditions based on discrete-mixture HMMs (DMHMMs). DMHMMs were originally proposed to reduce calculation costs in the decoding process. Recently, we have applied DMHMMs to noisy speech recognition, and found that they were effective for modeling noisy speech. Towards the further improvement of noise-robust speech recognition, we propose a novel normalization method for DMHMMs based on histogram equalization (HEQ). The HEQ method can compensate the nonlinear effects of additive noise. It is generally used for the feature space normalization of continuous-mixture HMM (CHMM) systems. In this paper, we propose both model space and feature space normalization of DMHMMs by using HEQ. In the model space normalization, codebooks of DMHMMs are modified by the transform function derived from the HEQ method. The proposed method was compared using both conventional CHMMs and DMHMMs. The results showed that the model space normalization of DMHMMs by multiple transform functions was effective for noise-robust speech recognition. Less

1.自发语音任务上的大词汇量连续语音识别在大词汇量连续语音识别中，我们研究了声学和语言模型无监督适应的几种方法，并在自发日语语料库（CSJ）上评估了这些方法。 LVCSR 系统采用全协方差矩阵作为声学模型。识别实验的结果表明，单词错误率（WER）从没有适应的19.17％下降到无监督适应的14.73％，并且通过基于词性对适应数据进行加权，降低到无监督适应的14.47％。此外，我们还比较了 CSJ 上连续混合 FRAM (CHMM) 系统和离散混合 HMM (DMHMM) 系统的性能。结果，DMHMM 系统提供了与 CHMM 系统几乎相同的性能，并且使用 6000 状态 24 混合 DMHMM 获得了 19.73% 的 WER，尽管到目前为止人们普遍认为 DMHMM 的识别错误率比 CHMM 高得多。 2．使用离散混合 HMM 的鲁棒语音识别我们引入了一种基于离散混合 HMM (DMHMM) 的噪声条件下鲁棒语音识别的新方法。 DMHMM 最初被提出是为了减少解码过程中的计算成本。最近，我们将 DMHMM 应用到噪声语音识别中，发现它们对于噪声语音建模非常有效。为了进一步改进抗噪声语音识别，我们提出了一种基于直方图均衡（HEQ）的 DMHMM 归一化方法。 HEQ方法可以补偿加性噪声的非线性影响。它通常用于连续混合 HMM (CHMM) 系统的特征空间归一化。在本文中，我们提出使用 HEQ 对 DMHMM 进行模型空间和特征空间归一化。在模型空间归一化中，DMHMM 的码本通过从 HEQ 方法导出的变换函数进行修改。使用传统 CHMM 和 DMHMM 对所提出的方法进行了比较。结果表明，通过多个变换函数对 DMHMM 进行模型空间归一化对于抗噪声语音识别是有效的。较少的

项目成果

話し言葉音声認識における教師なし適応の改善

改善口语语音识别中的无监督适应

• 发表时间: 2007
• 期刊: 情報処理学会東北支部研究会 06-6-A1-3
• 作者: Hiroyuki;Narita;Yasumasa;Sawamura;Akira;Hayashi;渥美雅保;Masayasu Atsumi;草間隆
• 通讯作者: 草間隆

マルチコンディションモデルを用いた音楽環境下の音声認識の検討

基于多条件模型的音乐环境下语音识别研究

• 发表时间: 2008
• 作者: Y. Takeda;M. Katoh;T. Kosaka;M. Kohda;大貫芳久
• 通讯作者: 大貫芳久

Noisy Speech recognition Based on Codebook Normalization of Discrete-Mixture HMMs

基于离散混合 HMM 码本归一化的噪声语音识别

• 发表时间: 2006
• 期刊: ASA/ASJ Forth Joint Meeting 1pSC27
• 作者: T.Kosaka;M.Katoh;M.Kohda
• 通讯作者: M.Kohda

Spontaneous speech recognition using discrete-mixture HMMs

使用离散混合 HMM 的自发语音识别

• 发表时间: 2007
• 作者: T. Kosaka;M. Katoh;M. Kohda
• 通讯作者: M. Kohda

Robust Speech Recognition and Understanding

强大的语音识别和理解

• 发表时间: 2007
• 作者: Tetsuya Takiguchi;R. Takashima;Y. Ariki;Hironori Matsumasa;Hyunsin Park;Tetsuya Takiguchi;高島遼一;高島遼一;高島遼一;室井貴司;吉井麻里子;室井貴司;三宅信之;室井貴司;三宅信之;朴玄信;三宅信之;高島遼一;朴玄信;室井貴司;松田博義;住田雄司;高島遼一;朴玄信;松田博義;三宅信之;住田雄司;松田博義;三宅信之;Tetsuya Takiguchi;Tetsuya Takiguchi
• 通讯作者: Tetsuya Takiguchi