Formant-gaps Features for Speaker Verification Using Whispered Speech

Naini, Abinay Reddy; Mv, Achuth Rao; Ghosh, Prasanta Kumar

doi:10.1109/icassp.2019.8682571

Cited by 10 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current mainstream WSR methods can be broadly classified into three categories. The first class of methods focuses on feature extraction [14][15][16][17][18], such as the Mel-scale Frequency Cepstral Coefficient (MFCC), Weighted Instantaneous Frequency, Auditory-inspired Amplitude Modulation Features (AAMFs), Formant-gaps (FoGs) features, and Weighted Modified Linear frequency cepstrum coefficients. Among them, MFCC has been used with GMM and has been used for the speaker recognition task.…”

Section: Introductionmentioning

confidence: 99%

Whisper40: A Multi-Person Chinese Whisper Speaker Recognition Dataset Containing Same-Text Neutral Speech

Yang,

Zhou

2024

Information

View full text Add to dashboard Cite

Whisper speaker recognition (WSR) has received extensive attention from researchers in recent years, and it plays an important role in medical, judicial, and other fields. Among them, the establishment of a whisper dataset is very important for the study of WSR. However, the existing whisper dataset suffers from the problems of a small number of speakers, short speech duration, and lack of neutral speech with the same-text as the whispered speech in the same dataset. To address this issue, we present Whisper40, a multi-person Chinese WSR dataset containing same-text neutral speech spanning around 655.90 min sourced from volunteers. In addition, we use the current state-of-the-art speaker recognition model to build a WSR baseline system and combine the idea of transfer learning for pre-training the speaker recognition model using neutral speech datasets and transfer the empirical knowledge of specific network layers to the WSR system. The Whisper40 and CHAINs datasets are then used to fine-tune the model with transferred specific layers. The experimental results show that the Whisper40 dataset is practical, and the time delay neural network (TDNN) model performs well in both the same/cross-scene experiments. The equal error rate (EER) of Chinese WSR after transfer learning is reduced by 27.62% in comparison.

show abstract

Section: Introductionmentioning

confidence: 99%

Whisper40: A Multi-Person Chinese Whisper Speaker Recognition Dataset Containing Same-Text Neutral Speech

Yang,

Zhou

2024

Information

View full text Add to dashboard Cite

show abstract

“…Speakers often use whispered speech in their day-to-day life. With the recent advancements in speech-enabled and virtual assistant devices [7], robust methods for whispered speech detection [8], recognition, and whispered speechbased speaker verification [9,10] had been developed. This motivated us to consider whispered speech together with neutral speech for recording device classification.…”

Section: Introductionmentioning

confidence: 99%

Dual Attention Pooling Network for Recording Device Classification Using Neutral and Whispered Speech

Naini

Singhal

Ghosh

2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

In this work, we proposed a method for recording device classification using the recorded speech signal. With the rapid increase in different mobile and professional recording devices, determining the source device has many applications in forensics and in further improving various speech-based applications. This paper proposes dual and single attention pooling-based convolutional neural networks (CNN) for recording device classification using neutral and whispered speech. Experiments using five recording devices with simultaneous direct recordings from 88 speakers speaking both in neutral and whisper and recordings from 21 mobile devices with simultaneous playback recordings reveal that the proposed dual attention pooling based CNN method performs better than the best baseline scheme. We show that we achieve a better performance in recording device classification with whispered speech recordings than corresponding neutral speech. We also demonstrate the importance of voiced/unvoiced speech and different frequency bands in classifying the recording devices.

show abstract