Artificial neural network features for speaker diarization
By S. Yella, Andreas Stolcke, Malcolm Slaney. 2014
49 citations recorded by the source corpus.
Speaker diarization finds contiguous speaker segments in an audio recording and clusters them by speaker identity, without any a-priori knowledge. Diarization is typically based on short-term spectral features such as Mel-frequency cepstral coefficients (MFCCs). Though these features carry average information about the vocal tract characteristics of a speaker, they are also susceptible to factors unrelated to the speaker identity. In this study, we propose an artificial neural network (ANN) architecture to learn a feature transform that is optimized for speaker diarization. We train a multi-hidden-layer ANN to judge whether two given speech segments came from the same or different speakers, using a shared transform of the input features that feeds into a bottleneck layer. We then use the bottleneck layer activations as features, either alone or in combination with baseline MFCC features in a multistream mode, for speaker diarization on test data. The resulting system is evaluated on various corpora of multi-party meetings. A combination of MFCC and ANN features gives up to 14% relative reduction in diarization error, demonstrating that these features are providing an additional independent source of knowledge.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Joon Son Chung
- Arsha Nagrani
- Andrew Zisserman
- Kristen Grauman
- Andrea Vedaldi
- Yoshua Bengio
- Shinji Watanabe
- Triantafyllos Afouras
Citations in the corpus
- VoxCeleb2: Deep Speaker Recognition (2018, methodology): “For example, [20] uses a Siamese feedforward DNN to discriminatively compare two voices, however this relies on pre-computed MFCC features, whilst [21] also learns the features instead of using MFCCs.”
- The Second DIHARD Diarization Challenge: Dataset, task, and baselines (2019, background): “, conversational telephone speech [2, 3, 4, 5, 6], broadcast [7, 8], or meeting [9, 10]).”
- Speaker identification and clustering using convolutional neural networks (2016, background): “also use the idea of speaker discriminative training and derive speaker-specific features from the hidden layer of a neural network of just 3 layers, which they subsequently feed into a GMM/HMM system for speaker clustering [19].”