[PDF][PDF] Large, pruned or continuous space language models on a gpu for statistical machine translation
H Schwenk, A Rousseau, M Attik - … We Ever Really Replace the N …, 2012 - aclanthology.org
Abstract Language models play an important role in large vocabulary speech recognition
and statistical machine translation systems. The dominant approach since several decades …
and statistical machine translation systems. The dominant approach since several decades …
Structured output layer neural network language models for speech recognition
This paper extends a novel neural network language model (NNLM) which relies on word
clustering to structure the output vocabulary: Structured OUtput Layer (SOUL) NNLM. This …
clustering to structure the output vocabulary: Structured OUtput Layer (SOUL) NNLM. This …
Models of tone for tonal and non-tonal languages
Conventional wisdom in automatic speech recognition asserts that pitch information is not
helpful in building speech recognizers for non-tonal languages and contributes only …
helpful in building speech recognizers for non-tonal languages and contributes only …
Mandarin lexical tone duration: Impact of speech style, word length, syllable position and prosodic position
Y Wu, M Adda-Decker, L Lamel - Speech Communication, 2023 - Elsevier
This study aims to increase our knowledge of Mandarin lexical tone duration in continuous
Mandarin speech. Related variation factors such as the number of syllable (s) in word, the …
Mandarin speech. Related variation factors such as the number of syllable (s) in word, the …
Two-pass decoding and cross-adaptation based system combination of end-to-end conformer and hybrid tdnn asr systems
Fundamental modelling differences between hybrid and end-to-end (E2E) automatic speech
recognition (ASR) systems create large diversity and complementarity among them. This …
recognition (ASR) systems create large diversity and complementarity among them. This …
[PDF][PDF] Multi-domain neural network language model.
T Alumäe - INTERSPEECH, 2013 - isca-archive.org
The paper describes a neural network language model that jointly models language in many
related domains. In addition to the traditional layers of a neural network language model, the …
related domains. In addition to the traditional layers of a neural network language model, the …
Language model cross adaptation for LVCSR system combination
State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often
combine outputs from multiple sub-systems that may even be developed at different sites …
combine outputs from multiple sub-systems that may even be developed at different sites …
[PDF][PDF] Automatic understanding of unwritten languages
O Adams - 2017 - minerva-access.unimelb.edu.au
Many of the world's languages are falling out of use without a written record and minimal
linguistic documentation. Language documentation is a slow process and there are an …
linguistic documentation. Language documentation is a slow process and there are an …
[PDF][PDF] Developing STT and KWS systems using limited language resources
This paper presents recent progress in developing speech-totext (STT) and keyword
spotting (KWS) systems for the 2014 IARPA-Babel evaluation. Systems have been …
spotting (KWS) systems for the 2014 IARPA-Babel evaluation. Systems have been …
[PDF][PDF] Phonotactic Language Recognition Using MLP Features.
This paper describes a very efficient Parallel Phone Recognizers followed by Language
Modeling (PPRLM) system in terms of both performance and processing speed. The system …
Modeling (PPRLM) system in terms of both performance and processing speed. The system …