Spontaneous speech recognition using a massively parallel decoder
Spontaneous speech recognition using a massively parallel decoder
复制标题
使用大规模并行解码器的自发语音识别
DOI：
10.21437/interspeech.2004-185
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
S. Furui
中科院分区：
文献类型：
--
作者：
T. Shinozaki;S. Furui
由于自发话语包含许多变化，独立于说话人和任务的一般模型不能很好地工作。在大规模并行解码器（MPD）框架下，提出了基于聚类的语言模型和声学模型相结合的方法。MPD是一种具有大量解码单元的并行解码器，其中每个单元分配给每个元素模型组合。它在并行计算机上高效运行，因此周转时间与使用单一型号和处理器的传统解码器相当。在使用自发日语语料库的演讲演讲进行的实验中，研究了两种类型的聚类模型：基于演讲的聚类模型和基于话语的聚类模型。基于话语的聚类模型在语言和声学建模方面的识别错误率明显低于基于讲座的聚类模型。研究还表明，在识别率方面，大约100个解码单元就足够了，在最佳设置下，与传统解码器相比，单词错误率降低了12%。
Since spontaneous utterances include many variations, speakerand task-independent general models do not work well. This paper proposes combining cluster-based language and acoustic models based on the framework of Massively Parallel Decoder (MPD). The MPD is a parallel decoder that has a large number of decoding units, in which each unit is assigned to each combination of element models. It runs efficiently on a parallel computer, and thus the turnaround time is comparable to conventional decoders using a single model and a processor. In the experiments conducted using lecture speeches from the Corpus of Spontaneous Japanese, two types of cluster models have been investigated: lecture-based cluster models and utterancebased cluster models. It has been confirmed that utterancebased cluster models give significantly lower recognition error rate than lecture-based cluster models in both language and acoustic modeling. It has also been shown that roughly 100 decoding units are enough in terms of recognition rate, and in the best setting, 12% reduction in word error rate was obtained in comparison with the conventional decoder.
使用日语自发语料库进行语音识别基准测试
DOI：
--
发表时间：
2003
期刊：
In Proc. ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition
影响因子：
--
作者：
T.Kawahara;H.Nanjo;T.Shinozaki;S.Furui
通讯作者：
S.Furui