Blind Speech Signal Quality Estimation for Speaker Verification Systems

Lavrentyeva, Galina; Volkova, Marina; Avdeeva, Anastasia; Novoselov, Sergey; Gorlanov, Artem; Andzhukaev, Tseren; Ivanov, Artem; Kozlov, Alexander

doi:10.21437/interspeech.2020-1826

Cited by 5 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We modified the publicly available implementation of [16] to support uncertainty propagation and used the original implementation as a baseline 3 , further referred to as VBx.…”

Section: Bayesian Hmm With Uncertainty Propagationmentioning

confidence: 99%

See 1 more Smart Citation

Magnitude-aware Probabilistic Speaker Embeddings

Kuzmin,

Fedorov,

Sholokhov

2022

Preprint

View full text Add to dashboard Cite

Recently, hyperspherical embeddings have established themselves as a dominant technique for face and voice recognition. Specifically, Euclidean space vector embeddings are learned to encode person-specific information in their direction while ignoring the magnitude. However, recent studies have shown that the magnitudes of the embeddings extracted by deep neural networks may indicate the quality of the corresponding inputs. This paper explores the properties of the magnitudes of the embeddings related to quality assessment and out-of-distribution detection. We propose a new probabilistic speaker embedding extractor using the information encoded in the embedding magnitude and leverage it in the speaker verification pipeline. We also propose several quality-aware diarization methods and incorporate the magnitudes in those. Our results indicate significant improvements over magnitude-agnostic baselines both in speaker verification and diarization tasks.

show abstract

“…We modified the publicly available implementation of [16] to support uncertainty propagation and used the original implementation as a baseline 3 , further referred to as VBx.…”

Section: Bayesian Hmm With Uncertainty Propagationmentioning

confidence: 99%

“…signal duration [1,2,3] may not be the most relevant characteristics in terms of recognition performance.…”

Section: Introductionmentioning

confidence: 99%

Magnitude-aware Probabilistic Speaker Embeddings

Kuzmin,

Fedorov,

Sholokhov

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…As an alternative method of separating speech and non-speech segments, we used the information about the acoustic characteristics of the signal from the microphone array of the AMI corpus. During evaluation, for each 0.5 s signal frame we estimated the SNR and RT60 parameters using the signal quality estimation (QE) model described in [9]. SNR and RT60 parameters were predicted for all 8 channels of the microphone array, so for each 0.5 s frame we obtained a vector of 16 values.…”

Section: Qe-vectors Systemmentioning

confidence: 99%

“…Recently, in addition to standard energy-based voice activity detectors, neural network-based VADs are gaining popularity, which allows one to obtain better resistance to noise conditions [8]. In this paper, we consider the use of the DNN-based VAD described in [9] for a diarization task applied to the AMI Meeting Corpus [10]. To deal with the inherent problems of multi-dialogue recordings such as speaker interruptions and the simultaneous utterances of multiple speakers, we examine options for fusing VAD with other speech analytic systems.…”

Section: Introductionmentioning

confidence: 99%

“…Information about acoustic conditions in terms of the speech-to-noise ratio (SNR) and reverberation time (RT60) for each audio segment can also be used to distinguish speech and non-speech frames. We apply an automatic quality estimation (QE) system, described in [9], to cluster estimated SNR-RT60 vectors into speech and non-speech clusters and thereby retrieve an approximate voice activity markup. Although this method is not accurate, we investigate its usefulness in fusing it with the base DNN-VAD.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2021

Self Cite

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

Deep Speaker Embeddings Based Online Diarization

Avdeeva

Novoselov²

2022

Speech and Computer

View full text Add to dashboard Cite

Blind Speech Signal Quality Estimation for Speaker Verification Systems

Cited by 5 publications

References 0 publications

Magnitude-aware Probabilistic Speaker Embeddings

Magnitude-aware Probabilistic Speaker Embeddings

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

Deep Speaker Embeddings Based Online Diarization

Contact Info

Product

Resources

About