Efficient lattice rescoring using recurrent neural network language models
Recurrent neural network language models (RNNLM) have become an increasingly popular
choice for state-of-the-art speech recognition systems due to their inherently strong …
choice for state-of-the-art speech recognition systems due to their inherently strong …
Restoring tone-marks in standard Yorùbá electronic text: improved model
FO Asahiah, OA Odejobi, ER Adagunodo - Computer Science, 2017 - journals.agh.edu.pl
Diacritic Restoration is a necessity in the processing of languages with Latinbased scripts
that utilizes letters outside the basic Latin alphabet used by English language. Yorùbá is one …
that utilizes letters outside the basic Latin alphabet used by English language. Yorùbá is one …
A Myanmar large vocabulary continuous speech recognition system
This paper presents a large vocabulary automatic speech recognition (ASR) system for
Myanmar. To the best of our knowledge, this is the first such system for the Myanmar …
Myanmar. To the best of our knowledge, this is the first such system for the Myanmar …
[PDF][PDF] The Cambridge University 2014 BOLT conversational telephone Mandarin Chinese LVCSR system for speech translation
This paper presents the development of the 2014 Cambridge University conversational
telephone Mandarin Chinese LVCSR system for the DARPA BOLT speech translation …
telephone Mandarin Chinese LVCSR system for the DARPA BOLT speech translation …
Semi-supervised acoustic model training by discriminative data selection from multiple asr systems' hypotheses
S Li, Y Akita, T Kawahara - IEEE/ACM Transactions on Audio …, 2016 - ieeexplore.ieee.org
While the performance of ASR systems depends on the size of the training data, it is very
costly to prepare accurate and faithful transcripts. In this paper, we investigate a …
costly to prepare accurate and faithful transcripts. In this paper, we investigate a …
Paraphrastic language models
Natural languages are known for their expressive richness. Many sentences can be used to
represent the same underlying meaning. Only modelling the observed surface word …
represent the same underlying meaning. Only modelling the observed surface word …
A hybrid input-type recurrent neural network for LVCSR language modeling
V Chunwijitra, A Chotimongkol… - EURASIP Journal on …, 2016 - Springer
Substantial amounts of resources are usually required to robustly develop a language
model for an open vocabulary speech recognition system as out-of-vocabulary (OOV) words …
model for an open vocabulary speech recognition system as out-of-vocabulary (OOV) words …
Speech Recognition and Text-to-Speech Synthesis
Automatic speech recognition (ASR) and text-to-speech (TTS) synthesis are two very
important modules in human-computer communication. With the development of deep …
important modules in human-computer communication. With the development of deep …
Paraphrastic recurrent neural network language models
Recurrent neural network language models (RNNLM) have become an increasingly popular
choice for state-of-the-art speech recognition systems. Linguistic factors in?? uencing the …
choice for state-of-the-art speech recognition systems. Linguistic factors in?? uencing the …
[PDF][PDF] A comprehensive study of staqc for deep code summarization
Learning the mapping between natural language (NL) and programming language, such as
retrieving or generating code snippets based on NL queries and annotating code snippets …
retrieving or generating code snippets based on NL queries and annotating code snippets …