Results 61 to 70 of about 2,263,293 (338)
The ins and outs of speaker recognition: lessons from VoxSRC 2020 [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2020 The VoxCeleb Speaker Recognition Challenge (VoxSRC) at Interspeech 2020 offers a challenging evaluation for speaker recognition systems, which includes celebrities playing different parts in movies.
Yoohwan Kwon +3 more
semanticscholar +1 more source
Real-time multilingual speech recognition and speaker diarization system based on Whisper segmentation [PDF]
PeerJ Computer ScienceThis research presents the development of a cutting-edge real-time multilingual speech recognition and speaker diarization system that leverages OpenAI’s Whisper model. The system specifically addresses the challenges of automatic speech recognition (ASR)
Ke-Ming Lyu +2 more
doaj +2 more sources
Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition [PDF]
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2019 Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector.
Xu Xiang +4 more
semanticscholar +1 more source
Constrained subword units for speaker recognition
, 2011 Paper 02, 6 S.Phonetic features have been proposed to overcome performance degradation in spectral speaker recognition in difficult acoustic conditions.
Baum, D. +3 more
core +1 more source
Pediatric Blood &Cancer, EarlyView.ABSTRACT Background Sickle cell disease (SCD) is a chronic, inherited hemoglobinopathy that requires frequent hospitalization for disease‐related complications. Canadian data on inpatient care is limited. This study compared caregiver‐reported hospital experiences of children with SCD to those with cystic fibrosis (CF), a chronic, autosomal recessive ...
Hailey M. Zwicker +11 more
wiley +1 more source
Advances in Electrical and Computer Engineering, 2015 Accuracy of an automatic speaker recognition system predominantly depends on speaker models and features that are used. An influence of the shape of auditory critical bands and a contribution of individual components of MFCC-based feature vectors are ...
JOKIC, I. +3 more
doaj +1 more source
Speaker recognition based on auditory impression: The role of familiarity with the speaker and language [PDF]
NBP: Nauka, bezbednost, policijaSpeech is a fundamental means of interpersonal communication. Speaker identification based on voice and speech can be analysed through two perspectives, expert listening by trained phoneticians, for the purpose of forensic speaker identification, and by ...
Šešum Mia +3 more
doaj +1 more source
Pediatric Blood &Cancer, EarlyView.ABSTRACT Background Central nervous system (CNS) involvement in childhood acute lymphoblastic leukemia (ALL) is assessed by cell counting and cytomorphology from cerebrospinal fluid (CSF) and is used for treatment stratification worldwide. The ratio of “CNS2” patients in clinical trials ranges from 3% to 40%, with unclear prognostic significance ...
Laura Almási +14 more
wiley +1 more source
Speaker-independent emotion recognition exploiting a psychologically-inspired binary cascade classification schema [PDF]
, 2012 06.08.13 KB. Ok to add accepted version to spiral, embargo period expired. SpringerIn this paper, a psychologically-inspired binary cascade classification schema is proposed for speech emotion recognition.
Kotti, Margarita, Paternò, Fabio
core +1 more source
Milestones in speaker recognition
Artificial Intelligence ReviewAbstractThis article reviews significant research in the domain of speaker recognition, i.e., the task of determining the speaker’s identity from its speech. Unlike conventional review articles, this document strives to be concise and selective, provide a historical context, and reach a wider audience. In this endeavour, a summary of selected key works
Rajib Sharma +5 more
openaire +1 more source