Supervised and unsupervised transfer learning for question answering
Although transfer learning has been shown to be successful for tasks like object and speech
recognition, its applicability to question answering (QA) has yet to be well-studied. In this …
recognition, its applicability to question answering (QA) has yet to be well-studied. In this …
Multistage data selection-based unsupervised speaker adaptation for personalized speech emotion recognition
This paper proposes an efficient speech emotion recognition (SER) approach that utilizes
personal voice data accumulated on personal devices. A representative weakness of …
personal voice data accumulated on personal devices. A representative weakness of …
Query by babbling: A research agenda
DW Oard - Proceedings of the first workshop on information and …, 2012 - dl.acm.org
The Spoken Web, an interconnected collection of spoken content accessed through audio-
only mobile phones, holds the promise of transforming information access for users in …
only mobile phones, holds the promise of transforming information access for users in …
Unsupervised rapid speaker adaptation based on selective eigenvoice merging for user-specific voice interaction
DJ Choi, JS Park, YH Oh - Engineering Applications of Artificial Intelligence, 2015 - Elsevier
Speaker adaptation transforms the standard speaker-independent acoustic models into an
adapted model relevant to the user (called the target speaker) in order to provide reliable …
adapted model relevant to the user (called the target speaker) in order to provide reliable …
Unsupervised domain adaptation for spoken document summarization with structured support vector machine
H Lee, Y Chou, YB Wang, L Lee - 2013 IEEE International …, 2013 - ieeexplore.ieee.org
Supervised approaches can learn a spoken document summarizer generating high-quality
summaries using a set of training examples matched to the domain of target documents …
summaries using a set of training examples matched to the domain of target documents …
Automatic speech recognition for resource–scarce environments
NT Kleynhans - 2013 - repository.nwu.ac.za
Automatic speech recognition (ASR) technology has matured over the past few decades and
has made significant impacts in a variety of fields, from assistive technologies to commercial …
has made significant impacts in a variety of fields, from assistive technologies to commercial …
Fast unsupervised adaptation based on efficient statistics accumulation using frame independent confidence within monophone states
This paper proposes a fast unsupervised acoustic model adaptation technique with efficient
statistics accumulation for speech recognition. Conventional adaptation techniques …
statistics accumulation for speech recognition. Conventional adaptation techniques …
[PDF][PDF] Unsupervised lattice-based acoustic model adaptation for speaker-dependent conversational telephone speech transcription.
K Thambiratnam, F Seide - INTERSPEECH, 2009 - isca-archive.org
This paper examines the application of lattice adaptation techniques to speaker-dependent
models for the purpose of conversational telephone speech transcription. Given sufficient …
models for the purpose of conversational telephone speech transcription. Given sufficient …
Cross-bandwidth adaptation for ASR systems
N Kleynhans, E Barnard - 2013 - researchspace.csir.co.za
Mismatches between application and training data greatly reduce the performance of
automatic speech recognition (ASR) systems. However, collecting suitable amounts of in …
automatic speech recognition (ASR) systems. However, collecting suitable amounts of in …
[引用][C] Call Transcription and Text Classification-A Review
AL Thakka, GK Anaswara, AE John, R Dhanusha… - International Journal of Computer …