In this work, we propose a framework to compensate the utterance information, which is used to normalize the lexical content. A hidden Markov model (HMM) based ...
Nov 15, 2018 · Abstract—This work investigates on explicitly utilizing utter- ance information for fixed phrase speaker verification (SV). In.
Mar 14, 2019 · The first 50 sessions of each known speaker's data were used for training, the last 50 for test; 0.6% of the phrases yielded unusable data. When ...
Rohan Kumar Das , Maulik C. Madhavi , Haizhou Li : Compensating Utterance Information in Fixed Phrase Speaker Verification. APSIPA 2018: 1708-1712.
Abstract. Most studies on speaker verification systems focus on long- duration utterances, which are composed of sufficient phonetic information.
Jul 10, 2024 · The proposed phonetic richness measure is found to be positively correlated with voice authentication scores across evaluation benchmarks.
Combining multiple systems based on different features and classifiers considerably reduces speaker verification error rate with short utterances. This work ...
Missing: Phrase | Show results with:Phrase
This paper gives an overview of automatic speaker recognition technology, with an emphasis on text-independent recognition.
Abstract. In practical settings, a speaker recognition system needs to iden- tify a speaker given a short utterance, while the enrollment.
Jan 29, 2020 · The short duration of an input utterance is one of the most critical threats that degrade the performance of speaker verification systems.