Results 31 to 40 of about 132,794 (332)
Chinese Dialogue Intention Classification Based on Multi-Model Ensemble
IEEE Access, 2019 In dialogue systems, understanding the user utterances is crucial for providing appropriate responses. A traditional dialogue act classification (DA) task is to classify each user reply into “ACCEPT, REJECT, PROPOSE, and others”.
Manshu Tu, Bing Wang, Xuemin Zhao
doaj +1 more source
Convex separable problems with linear and box constraints [PDF]
, 2014 In this work, we focus on separable convex optimization problems with linear and box constraints and compute the solution in closed-form as a function of some Lagrange multipliers that can be easily computed in a finite number of iterations.
D'Amico, Antonio A. +2 more
core +3 more sources
Acoustic effects of style of speech [PDF]
The Journal of the Acoustical Society of America, 1974 Recordings were made of nine subjects producing test words in seven different styles, varying from completely informal conversation to reading the test words in lists. The subjects were all educated male speakers of standard English who had lived in Southern California from an early age.
P, Ladefoged, I, Kameny, W, Brackenridge
openaire +2 more sources
Relevancy between Objects Based on Common Sense for Semantic Segmentation
Applied Sciences, 2022 Research on image classification sparked the latest deep-learning boom. Many downstream tasks, including semantic segmentation, benefit from it. The state-of-the-art semantic segmentation models are all based on deep learning, and they sometimes make ...
Jun Zhou, Xing Bai, Qin Zhang
doaj +1 more source
Applied Sciences, 2018 Common sound source localization algorithms focus on localizing all the active sources in the environment. While the source identities are generally unknown, retrieving the location of a speaker of interest requires extra effort. This paper addresses the
Ziteng Wang, Junfeng Li, Yonghong Yan
doaj +1 more source
Direct Acoustics-to-Word Models for English Conversational Speech Recognition
, 2017 Recent work on end-to-end automatic speech recognition (ASR) has shown that the connectionist temporal classification (CTC) loss can be used to convert acoustics to phone or character sequences.
Audhkhasi, Kartik +4 more
core +1 more source
Modeling speech imitation and ecological learning of auditory-motor maps. [PDF]
, 2013 Classical models of speech consider an antero-posterior distinction between perceptive and productive functions. However, the selective alteration of neural activity in speech motor centers, via transcranial magnetic stimulation, was shown to affect ...
Badino, L +4 more
core +2 more sources
Acoustic segmentation of speech [PDF]
International Journal of Man-Machine Studies, 1970 A brief argument is presented for the need for automatic speech segmentation both to facilitate automatic speech recognition and for its theoretical linguistic importance. The problem of speech segmentation in the acoustic domain using a digital computer is examined in detail, that is, of determining an acoustic partition in time which has linguistic ...
openaire +1 more source
Polyphonic Piano Transcription with a Note-Based Music Language Model
Applied Sciences, 2018 This paper proposes a note-based music language model (MLM) for improving note-level polyphonic piano transcription. The MLM is based on the recurrent structure, which could model the temporal correlations between notes in music sequences. To combine the
Qi Wang, Ruohua Zhou, Yonghong Yan
doaj +1 more source
Modeling Speech Sound Radiation With Different Degrees of Realism for Articulatory Synthesis
IEEE Access, 2022 Articulatory synthesis is based on modeling various physical phenomena of speech production, including sound radiation from the mouth. With regard to sound radiation, the most common approach is to approximate it in terms of a simple spherical source of ...
Peter Birkholz +5 more
doaj +1 more source