Efficient lattice rescoring using recurrent neural network language models

X Liu, Y Wang, X Chen, MJF Gales… - … on Acoustics, Speech …, 2014 - ieeexplore.ieee.org
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 …

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 …

A Myanmar large vocabulary continuous speech recognition system

HMS Naing, AM Hlaing, WP Pa, X Hu… - 2015 Asia-Pacific …, 2015 - ieeexplore.ieee.org
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 …

[PDF][PDF] The Cambridge University 2014 BOLT conversational telephone Mandarin Chinese LVCSR system for speech translation

X Liu, F Flego, L Wang, C Zhang… - … Annual Conference of …, 2015 - mi.eng.cam.ac.uk
This paper presents the development of the 2014 Cambridge University conversational
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 …

Paraphrastic language models

X Liu, MJF Gales, PC Woodland - Computer Speech & Language, 2014 - Elsevier
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 …

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 …

Speech Recognition and Text-to-Speech Synthesis

L Sun, S Kang, X Liu, H Meng - Chinese Language Resources: Data …, 2023 - Springer
Automatic speech recognition (ASR) and text-to-speech (TTS) synthesis are two very
important modules in human-computer communication. With the development of deep …

Paraphrastic recurrent neural network language models

X Liu, X Chen, MJF Gales… - 2015 IEEE International …, 2015 - ieeexplore.ieee.org
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 …

[PDF][PDF] A comprehensive study of staqc for deep code summarization

JR Peddamail, Z Yao, Z Wang, H Sun - Proceedings of the 24th ACM …, 2018 - kdd.org
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 …