Histogram Transform-based Speaker Identification

Abstract

A novel text-independent speaker identification (SI) method is proposed. This method uses the Mel-frequency Cepstral coefficients (MFCCs) and the dynamic information among adjacent frames as feature sets to capture speaker's characteristics. In order to utilize dynamic information, we design super-MFCCs features by cascading three neighboring MFCCs frames together. The probability density function (PDF) of these super-MFCCs features is estimated by the recently proposed histogram transform~(HT) method, which generates more training data by random transforms to realize the histogram PDF estimation and recedes the commonly occurred discontinuity problem in multivariate histograms computing. Compared to the conventional PDF estimation methods, such as Gaussian mixture models, the HT model shows promising improvement in the SI performance.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyma2018histogram

Related papers

• Pitch-synchronous DCT Features: A Pilot Study On Speaker Identification (2018)0.00
• The Exploitation Of Multiple Feature Extraction Techniques For Speaker Identification In Emotional States Under Disguised Voices (2021)2.26
• Prosodic-enhanced Siamese Convolutional Neural Networks For Cross-device Text-independent Speaker Verification (2018)8.35
• Multi-label Training For Text-independent Speaker Identification (2022)0.00
• Speaker Fuzzy Fingerprints: Benchmarking Text-based Identification In Multiparty Dialogues (2025)0.00
• Speaker Identification In The Shouted Environment Using Suprasegmental Hidden Markov Models (2017)10.85
• PCA/LDA Approach For Text-independent Speaker Recognition (2016)5.24
• T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model (2020)0.00