Network-based mobile services, such as speech-to-speech translation and voice search, enable the construction of large-scale log database including speech. We have developed a smartphone application called VoiceTra for speech-to-speech translation and have collected 10, 000, 000 utterances so far. This huge corpus is unique in size and spatio-temporal information, it contains information on anonymized user locations. This spatio-temporal corpus can be used for improving the accuracy of its speech recognition and machine translation, and it will open the door for the study of the location dependency of vocabulary and new applications for location-based services. This paper first analyzes the corpus and then presents a novel method for classifying utterances using linguistic and non-linguistic information. L2-regularized Logistic Regression is used for utterance classification. Our experiments performed on the VoiceTra log corpus revealed that our proposed method outperformed baseline methods in terms of F measure.
|Number of pages||5|
|Journal||Proceedings - IEEE International Conference on Mobile Data Management|
|Publication status||Published - 2013 Sep 11|
|Event||14th International Conference on Mobile Data Management, MDM 2013 - Milan, Italy|
Duration: 2013 Jun 3 → 2013 Jun 6
- speech-to-speech translation
ASJC Scopus subject areas