The 2019 NIST Speaker Recognition Evaluation CTS Challenge

Sadjadi, Seyed Omid; Greenberg, Craig S.; Singer, Elliot; Reynolds, Douglas A.; Mason, Lisa P.; Hernandez-Cordero, Jaime

doi:10.21437/odyssey.2020-38

Cited by 18 publications

(17 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additional research must be conducted to increase the accuracy and efficacy of the employed technologies if contact tracing apps are to play an impactful role in infectious disease control moving forward. Toward this end, the National Institute of Standards and Technology, along with the MIT PACT (Private Automated Contact Tracing) project, has issued its "too close for too long" challenge to engage with research organizations worldwide concerning noise reduction and more precise distance and temporal estimation of Bluetooth LE signals [100].…”

Section: App Efficacy and Perception Recommendationsmentioning

confidence: 99%

Contact Tracing Apps: Lessons Learned on Privacy, Autonomy, and the Need for Detailed and Thoughtful Implementation

Hogan¹,

Macedo²,

Macha³

et al. 2021

JMIR Med Inform

View full text Add to dashboard Cite

The global and national response to the COVID-19 pandemic has been inadequate due to a collective lack of preparation and a shortage of available tools for responding to a large-scale pandemic. By applying lessons learned to create better preventative methods and speedier interventions, the harm of a future pandemic may be dramatically reduced. One potential measure is the widespread use of contact tracing apps. While such apps were designed to combat the COVID-19 pandemic, the time scale in which these apps were deployed proved a significant barrier to efficacy. Many companies and governments sprinted to deploy contact tracing apps that were not properly vetted for performance, privacy, or security issues. The hasty development of incomplete contact tracing apps undermined public trust and negatively influenced perceptions of app efficacy. As a result, many of these apps had poor voluntary public uptake, which greatly decreased the apps’ efficacy. Now, with lessons learned from this pandemic, groups can better design and test apps in preparation for the future. In this viewpoint, we outline common strategies employed for contact tracing apps, detail the successes and shortcomings of several prominent apps, and describe lessons learned that may be used to shape effective contact tracing apps for the present and future. Future app designers can keep these lessons in mind to create a version that is suitable for their local culture, especially with regard to local attitudes toward privacy-utility tradeoffs during public health crises.

show abstract

Section: App Efficacy and Perception Recommendationsmentioning

confidence: 99%

Contact Tracing Apps: Lessons Learned on Privacy, Autonomy, and the Need for Detailed and Thoughtful Implementation

Hogan¹,

Macedo²,

Macha³

et al. 2021

JMIR Med Inform

View full text Add to dashboard Cite

show abstract

“…The NIST SRE 2019 evaluation dataset [26] is composed of PSTN and VoIP data collected outside of North America, spoken in Tunisian Arabic, and contains 1364 enrollment and 13,587 test utterances recorded at 8 kHz. Speakers were encouraged to use different telephone instruments (e.g., cell phones, landlines) in a variety of settings (e.g., a noisy cafe, a quiet office) for their initiated calls [26]. Enrollment segments approximately contain 60 s of speech to build the model of the target speaker.…”

Section: Datasetsmentioning

confidence: 99%

Application of Fusion of Various Spontaneous Speech Analytics Methods for Improving Far-Field Neural-Based Diarization

et al. 2021

View full text Add to dashboard Cite

Recently developed methods in spontaneous speech analytics require the use of speaker separation based on audio data, referred to as diarization. It is applied to widespread use cases, such as meeting transcription based on recordings from distant microphones and the extraction of the target speaker’s voice profiles from noisy audio. However, speech recognition and analysis can be hindered by background and point-source noise, overlapping speech, and reverberation, which all affect diarization quality in conjunction with each other. To compensate for the impact of these factors, there are a variety of supportive speech analytics methods, such as quality assessments in terms of SNR and RT60 reverberation time metrics, overlapping speech detection, instant speaker number estimation, etc. The improvements in speaker verification methods have benefits in the area of speaker separation as well. This paper introduces several approaches aimed towards improving diarization system quality. The presented experimental results demonstrate the possibility of refining initial speaker labels from neural-based VAD data by means of fusion with labels from quality estimation models, overlapping speech detectors, and speaker number estimation models, which contain CNN and LSTM modules. Such fusing approaches allow us to significantly decrease DER values compared to standalone VAD methods. Cases of ideal VAD labeling are utilized to show the positive impact of ResNet-101 neural networks on diarization quality in comparison with basic x-vectors and ECAPA-TDNN architectures trained on 8 kHz data. Moreover, this paper highlights the advantage of spectral clustering over other clustering methods applied to diarization. The overall quality of diarization is improved at all stages of the pipeline, and the combination of various speech analytics methods makes a significant contribution to the improvement of diarization quality.

show abstract

“…Evaluasi dan pengembangan sistem pengenalan pembicara sampai saat ini tetap dilakukan. NIST mengambil peran tersebut dan yang terbaru evaluasi dan pengembangan sistem pengenalan pembicara tersebut difokuskan pada performa dan penemuan ide baru (Greenberg et al, 2020;Sadjadi et al, 2020). Performa sistem pengenalan pembicara umumnya dipengaruhi, salah satunya, oleh metode ekstraksi ciri.…”

Section: Pendahuluanunclassified

Sistem Pengenalan Pembicara dengan Metode Wavelet-MCFF dan Pengklasifikasi Hidden Markov Models (HMM)

Hidayat¹,

Anas

Yusuf³

et al. 2021

JTIIK

View full text Add to dashboard Cite

Penelitian pengolahan sinyal digital yang berfokus pada pengenalan pembicara telah dimulai sejak beberapa dekade yang lalu, dan telah menghasilkan banyak metode-metode pengenalan pembicara. Di antara algoritma pembentukan koefisien ciri yang telah dikembangkan tersebut, ada dua algoritma yang dapat memberikan akurasi yang tinggi jika diterapkan pada sistem, yaitu Mel Frequency Cepstral Coefficient (MFCC) dan Wavelet. Penelitian ini bertujuan untuk menguji dan memilih kanal terbaik dari proses wavelet-MFCC yang dapat dijadikan sebagai koefisien ciri baru untuk diterapkan pada sistem pengenal pembicara. Koefisien ciri baru tersebut kemudian disebut dengan koefisien ciri Wavelet-MFCC. Kofisien ini dibentuk dari merubah kanal hasil dekomposisi wavelet, yaitu kanal aproksimasi (cA), kanal detail (cD), dan penggabungannya (cAcD), menjadi koefisien MFCC. Metode dekomposisi wavelet yang digunakan adalah metode dyadic dengan menerapkan level dekomposisi level 1 dan level 2. Setiap koefisien ciri kemudian menjadi inputan pada sistem pengklasifikasi Hidden Markov Models (HMM). Keluaran dari HMM kemudian dihitung akurasinya dan dianalisis. Dari pengujian yang dilakukan, diperoleh bahwa kanal detail (cD) sebagai ciri dapat memberikan akurasi yang sama dengan menggunakan kanal gabungan (cAcD) dan lebih tinggi dari kanal aproksimasi (cA), dengan akurasi sebesar 95%. Hal ini menunjukkan bahwa, kanal detail pada dekomposisi level 1 menyimpan ciri suara dari setiap pembicara sehingga sudah cukup untuk dijadikan sebagai koefisien ciri. Maka, penggunaan dekomposisi level 1 dan kanal detail cD sebagai ciri Wavelet-MFCC pada sistem pengenalan pembicara dapat meringankan dan mempercepat proses komputasi. AbstractResearch in digital signal that focused on speaker recognition has begun since decades ago, and has resulted many speaker recognition methods. there are two algorithms that can provide high accuracy in recognition system, which are Mel Frequency Cepstral Coefficient (MFCC) and Wavelet. the aims of this study is to examine and chose the best channel from wavelet-MFCC process that can be used as new feature coefficient, then called as Wavelet-MFCC features coefficient. The coefficient is built by converting the wavelet decomposition channels, which are approximation (cA), detail (cD), and its combination (cAcD), into the MFCC coefficient. Wavelet dyadic decomposition with level 1 and level 2 of decomposition is applied. Each feature coefficient acts as an input to the HMM classifier. The accuracy of the HMM output is calculated, then analyzed. The obtained results show that the detail chanel (cD) achieve equal accuracy as the combination chanel (cAcD), and higher accuracy compared to aproximation channel (cA), with accuracy 95%. Thus, it can be conclude that the detail channel on level 1 decomposition contains features of each speaker's. Then, cD is enough to be used as a Wavelet-MFCC feature. Thus, its implementation in the SRS can ease and speed up the computing process.

show abstract

The 2019 NIST Speaker Recognition Evaluation CTS Challenge

Cited by 18 publications

References 8 publications

Contact Tracing Apps: Lessons Learned on Privacy, Autonomy, and the Need for Detailed and Thoughtful Implementation

Contact Tracing Apps: Lessons Learned on Privacy, Autonomy, and the Need for Detailed and Thoughtful Implementation

Application of Fusion of Various Spontaneous Speech Analytics Methods for Improving Far-Field Neural-Based Diarization

Sistem Pengenalan Pembicara dengan Metode Wavelet-MCFF dan Pengklasifikasi Hidden Markov Models (HMM)

Contact Info

Product

Resources

About