Speech recognition has of late become a practical technology for real world applications. For the purpose of research and development in speech-driven retrieval, which facilitates retrieving information with spoken queries, we organized the speech-driven retrieval subtask in the NTCIR-3 Web retrieval task. Search topics for the Web retrieval main task were dictated by ten speakers and were reco...

The construction of high-performance acoustic models for certain speech recognition tasks is very costly and time-consuming, since it most often requires the collection and transcription of large amounts of task-specific speech data. In this paper acoustic modeling for spoken dialogue systems based on unsupervised selective training is examined. The main idea is to select those training utteran...

The key factors helping people to understand the synthesized voices of text-to-speech system are the naturalness and the intelligibility. However, making more natural voices remains a difficult task because of the speech data’s scarcity. With data limited corpus, prosodic information such as tone, intonation, Part-of-Speech is added to ensure the quality of synthetic speech. In the paper, we in...

Speech recognition has of late become a practical technology for real world applications. For the purpose of research and development in speech-driven retrieval, which facilitates retrieving information with spoken queries, we organized the speech-driven retrieval subtask in the NTCIR-3 Web retrieval task. Search topics for the Web retrieval main task were dictated by ten speakers and recorded ...

In this paper we describe a new testbed for developing speech recognition algorithms a VoiceMail transcription task, analogous to other tasks such as the Switchboard, CallHome, and the Hub 4 tasks, which are currently used by speech recognition researchers. We describe the collection and use of a new VoiceMail database (that is available to the research community through the LDC), and also desc...

Sequence-to-sequence attentional-based neural network architectures have been shown to provide a powerful model for machine translation and speech recognition. Recently, several works have attempted to extend the models for end-to-end speech translation task. However, the usefulness of these models were only investigated on language pairs with similar syntax and word order (e.g., English-French...

Acoustic models for state-of-the-art DNN-based speech recognition systems are typically trained using at least several hundred hours of task-specific training data. However, this amount of training data is not always available for some applications. In this paper, we investigate how to use an adult speech corpus to improve DNN-based automatic speech recognition for non-native children's speech....

The goal of this work is to present a text-to-phoneme conversion (TPC) check tool for generating dictionaries usable for Speech Synthesis and Speech Recognition which includes phonetic and linguistic knowledge. The aim is to improve and accelerate the task of producing canonic pronunciation dictionaries in languages where no simple text-to-phoneme conversion is possible. The prototype was devel...