Robust speaker identification via fusion of subglottal resonances and cepstral features

Abstract

This letter investigates the use of subglottal resonances (SGRs) for noise-robust speaker identification (SID). It is motivated by the speaker specificity and stationarity of subglottal acoustics, and the development of noise-robust SGR estimation algorithms which are reliable at low signal-to-noise ratios for large datasets. A two-stage framework is proposed which combines the SGRs with different cepstral features. The cepstral features are used in the first stage to reduce the number of target speakers for a test utterance, and then SGRs are used as complementary second-stage features to conduct identification. Experiments with the TIMIT and NIST 2008 databases show that SGRs, when used in conjunction with power-normalized cepstral coefficients and linear prediction cepstral coefficients, can improve the performance significantly (2%–6% absolute accuracy improvement) across all noise conditions in mismatched situations.

Adaptive wavelet thresholding with robust hybrid features for text-independent speaker identification system

“…The testing is done on clean and noisy conditions to test the robustness of the proposed feature extraction algorithm, 4 noise types are chosen from the Noisex-92 noise dataset (babble, factory 1, pink and white) that are added to the test utterances with SNR levels 0, 5, 10 and 15 db. The results showed that the proposed features outperforms baseline features (PNCC and GFCC) and other proposed works Islam et al, in 2016, Korba et al, in 2018, Guo et al, in 2017and Ajgou et al in 2016, so it's a promising approach for extracting robust features and increasing speaker identification rate.…”

“…Figure 5. Comparison with other studies: (a) with work proposed by [1], (b) with work proposed by[18], (c) with work proposed by[38], and (d) with work proposed by[39] …”

Characteristic Sequence Analysis of Giant Panda Voiceprint

“…After the 1980s, characteristic parameters such as time domain decomposition, frequency domain decomposition, and wavelet packet node energy also gradually appeared and were widely used [6]. Jinxi Guo et al studied the recognition system in the noise environment [7] and made some achievements and progress.…”

DEEPTALK: Vocal Style Encoding for Speaker Recognition and Speech Synthesis

“…A majority of automatic speaker recognition systems use only the physiological speech features due to their high discriminability and ease of characterization [2]. However, such automatic speaker recognition systems are vulnerable to audio degradations, such as background noise and channel effects [3]. Behavioral speech characteristics, while being susceptible to intra-user variations, are considered robust to audio degradations [4].…”