Mean Hilbert envelope coefficients (MHEC) for robust speaker and language identification

Sadjadi, Seyed Omid; Hansen, John H. L.

doi:10.1016/j.specom.2015.04.005

Cited by 74 publications

(47 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is noted that the performance on the proposed method changes under clean condition depending on noise type due to using different noise dictionaries, whereas the baseline methods do not, which is to be expected. The general trend across all noise types is that all the enhancement algorithms does improve performance for SNR≤10 dB, which is in line with the results obtained in [5]. The proposed method outperforms the other algorithms with a substantial margin in this range of SNR levels except for the case of babble noise.…”

Section: Speaker Verification Resultssupporting

confidence: 87%

“…al. [5] investigate the performance of speech enhancement techniques for speaker identification under noisy and mis-matched conditions and conclude that for low signal-to-noise ratios (0, 5 and 10 dB), there is generally a performance gain, but that enhancement can degrade performance at higher SNR and perform worse than using the noisy signal directly. The authors furthermore propose to use mean Hilbert envelope coefficients (MHEC) as features and show that they outperform conventional mel-frequency cepstrum coefficients (MFCC).…”

Section: Introductionmentioning

confidence: 99%

“…This is similar to [5], but here we consider text-dependent speaker verification instead of speaker recognition and the evaluation is done on the recent RSR2015 database. We furthermore propose to apply sparse coding to the task of front-end speech enhancement for text-dependent speaker verification.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Speaker-Dependent Dictionary-Based Speech Enhancement for Text-Dependent Speaker Verification

Thomsen¹,

Thomsen²,

Lindberg³

et al. 2016

Interspeech 2016

View full text Add to dashboard Cite

The problem of text-dependent speaker verification under noisy conditions is becoming ever more relevant, due to increased usage for authentication in real-world applications. Classical methods for noise reduction such as spectral subtraction and Wiener filtering introduce distortion and do not perform well in this setting. In this work we compare the performance of different noise reduction methods under different noise conditions in terms of speaker verification when the text is known and the system is trained on clean data (mis-matched conditions). We furthermore propose a new approach based on dictionary-based noise reduction and compare it to the baseline methods.

show abstract

Section: Speaker Verification Resultssupporting

confidence: 87%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Speaker-Dependent Dictionary-Based Speech Enhancement for Text-Dependent Speaker Verification

Thomsen¹,

Thomsen²,

Lindberg³

et al. 2016

Interspeech 2016

View full text Add to dashboard Cite

show abstract

“…However, it should be noted that power spectral subtraction is used in the preprocessing to suppress additive noise, which probably increased the recognition rate for both the baseline methods, and the proposed method. Two-dimensional (2D) [19À20], [23], [31], [34], [38], [47], [49], [51], [54À58] auto-regressive (AR) spectrograms are used in [43] to eliminate noise effects. In this method, two LP analysis, one in time domain, and the other in frequency domain, are applied to speech signal.…”

Section: Robust Features Against Additive Noisementioning

confidence: 99%

A Review on Feature Extraction for Speaker Recognition under Degraded Conditions

DİŞKEN

Tüfekçi

Sarıbulut

et al. 2016

IETE Technical Review

View full text Add to dashboard Cite

Speech is a signal that includes speaker's emotion, characteristic specification, phonemeinformation etc. Various methods have been proposed for speaker recognition by extracting specifications of a given utterance. Among them, short-term cepstral features are used excessively in speech, and speaker recognition areas because of their low complexity, and high performance in controlled environments. On the other hand, their performances decrease dramatically under degraded conditions such as channel mismatch, additive noise, emotional variability, etc. In this paper, a literature review on speaker-specific information extraction from speech is presented by considering the latest studies offering solutions to the aforementioned problem. The studies are categorized in three groups considering their robustness against channel mismatch, additive noise, and other degradations such as vocal effort, emotion mismatch, etc. For a more understandable representation, they are also classified into two tables by utilizing their classification methods, and used data-sets.

show abstract

“…Instead of using the MFCCs, other types of features are proposed by the researchers to increase the robustness of the recognizers [4][5][6][7][8]. Also, since the MFCCs are widely adopted, many researchers have made effort to improve its robustness under noise by modifying, or changing, some processes in the conventional scheme [9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

A robust polynomial regression-based voice activity detector for speaker verification

DİŞKEN

Tüfekçi

Çevik

2017

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Robustness against background noise is a major research area for speech-related applications such as speech recognition and speaker recognition. One of the many solutions for this problem is to detect speech-dominant regions by using a voice activity detector (VAD). In this paper, a second-order polynomial regression-based algorithm is proposed with a similar function as a VAD for text-independent speaker verification systems. The proposed method aims to separate steady noise/silence regions, steady speech regions, and speech onset/offset regions. The regression is applied independently to each filter band of a mel spectrum, which makes the algorithm fit seamlessly to the conventional extraction process of the mel-frequency cepstral coefficients (MFCCs). The kmeans algorithm is also applied to estimate average noise energy in each band for spectral subtraction. A pseudo SNR-dependent linear thresholding for the final VAD output decision is introduced based on the k-means energy centers. This thresholding considers the speech presence in each band. Conventional VADs usually neglect the deteriorative effects of the additive noise in the speech regions. Contrary to this, the proposed method decides not only for the speech presence, but also if the frame is dominated by the speech, or the noise. Performance of the proposed algorithm is compared with a continuous noise tracking method, and another VAD method in speaker verification experiments, where five different noise types at five different SNR levels were considered. The proposed algorithm showed superior verification performance both with the conventional GMM-UBM method, and the stateof-the-art i-vector method.

show abstract

Mean Hilbert envelope coefficients (MHEC) for robust speaker and language identification

Cited by 74 publications

References 52 publications

Speaker-Dependent Dictionary-Based Speech Enhancement for Text-Dependent Speaker Verification

Speaker-Dependent Dictionary-Based Speech Enhancement for Text-Dependent Speaker Verification

A Review on Feature Extraction for Speaker Recognition under Degraded Conditions

A robust polynomial regression-based voice activity detector for speaker verification

Contact Info

Product

Resources

About