Dec 12, 2014 · To address spoken queries, we propose a com- bination of candidates obtained through some ASR systems which are based on syllable or word units.
This paper presents an automatic method for discriminating IV and OOV terms by using the confidence scores of spoken queries through ...
Sopoken Term Detection Based on a Syllable N-gram Index at the NTCIR-11 SpokenQuery&Doc Task · Proceedings of the 11th NTCIR Conference on Evaluation of ...
Sopoken Term Detection Based on a Syllable N-gram Index at the NTCIR-11 SpokenQuery&Doc Task. ... Spoken Term Detection by N-gram Index with Exact Distance for ...
Sopoken Term Detection Based on a Syllable N-gram Index at the NTCIR-11 SpokenQuery&Doc Task Nagisa Sakamoto, Kazumasa Yamamoto and Seiichi Nakagawa [Pdf] ...
They were either word-based trigram or syllable-based tri- gram, which result in word-based transcription and syllable- based transcription, respectively.
Missing: Sopoken | Show results with:Sopoken
Robust/fast out-of-vocabulary spoken term detection by N-gram index with exact distance through text/speech input · Strict Distance Measure for a Spoken Term ...
The NTCIR-11 SpokenQuery&Doc Task [2] provides a common evaluation framework for researchers interested in tasks of spoken term detection (STD) and spoken ...
Missing: Sopoken | Show results with:Sopoken
Combining Subword and State-level Dissimilarity Measures for Improved Spoken Term Detection in NTCIR-11 SpokenQuery&Doc Task.
2014. pdf dblp · Sopoken Term Detection Based on a Syllable N-gram Index at the NTCIR-11 SpokenQuery&Doc Task · Nagisa Sakamoto | Kazumasa Yamamoto | Seiichi ...