VoxCeleb 2019 challenge assesses speaker recognition in uncontrolled settings.
problem Evaluate speaker recognition technology in unconstrained data.
method Public dataset, challenge, and workshop at Interspeech 2019.
result Baseline results and discussions provided.
Study shows emotion affects speaker recognition and vice versa.
problem Dependencies between emotion and speaker recognition.
method Transfer learning and fine-tuning for emotion classification.
result Fine-tuning improves emotion recognition performance by 30.40% on IEMOCAP, 7.99% on MSP-Podcast, and 8.61% on Crema-D.
Improved speaker recognition with deep metric learning.
problem Performance gap between training and unseen speakers.
method Optimized speaker embedding model with prototypical network loss (PNL).
result Outperforms state-of-the-art models in speaker verification and identification.
A new deep neural network improves short-speech recognition.
problem Improving speaker recognition for short-duration speech segments.
method Proposes UtterIdNet, a novel deep neural network architecture.
result Consistent and stable performance for short segments, especially sub-second durations.
Deep learning improves speaker recognition verification and identification.
problem Limited progress in speaker recognition for 5-6 years.
method Applied deep learning techniques in speaker verification and identification.
result Deep learning becomes the state-of-the-art solution for speaker recognition.
The paper proposes deep normalization to improve speaker recognition performance.
problem Non-Gaussian and non-homogeneous distributions of deep speaker vectors negatively impact speaker recognition.
method Proposes a deep normalization approach based on a novel discriminative normalization flow (DNF) model.
result DNF-based normalization delivers substantial performance gains and strong generalization capability.
NIST CTS Superset offers a large dataset for telephony speaker recognition.
problem Lack of a large-scale, uniform dataset for telephony speaker recognition.
method Compilation of speech segments from multiple corpora, including Greybeard, Switchboard, and Mixer series.
result Results on the NIST 2020 CTS Speaker Recognition Challenge serve as a reference baseline.
Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains are possible using a single DNN for both speaker and language recognition. The u…
In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) …
The NL score optimizes speaker recognition tasks.
problem Improving speaker recognition accuracy.
method Established the theory of optimal scores based on normalized likelihood.
result NL score is equivalent to PLDA likelihood ratio under certain conditions.
Meta-learning framework improves short utterance speaker recognition.
problem Poor performance of existing models with short utterances.
method Prototypical Networks with support and query sets, enforcing classification against entire training set.
result Significant performance gains on VoxCeleb datasets.
Personal VAD detects target speaker voice activity efficiently.
problem Efficiently detect target speaker voice activity for reduced computational cost and battery usage.
method Trains a neural network conditioned on speaker embedding or verification score, outputs probabilities for three speech classes.
result Trained model with 130K parameters outperforms combined standard VAD and speaker recognition networks.
Improved far-field speaker verification for short utterances in noisy conditions.
problem Challenges in speaker verification on short utterances in uncontrolled noisy environments.
method Used deep neural network architectures (TDNN and ResNet) and experimented with various embedding extractors and training procedures.
result ResNet architectures outperform x-vector approach in speaker verification quality for both long and short utterances.
In this paper we describe the recent advancements made in the IBM i-vector speaker recognition system for conversational speech. In particular, we identify key techniques that contribute to significant improvements in performance of our system, and quantify their contributions. The techniques include: 1) a nearest-neig…
Study combines speaker verification and voice trigger detection in a single network.
problem Separate training for speaker verification and voice trigger detection.
method Multi-task learning with a single network trained on both tasks.
result Single network achieves comparable accuracy to independent models for each task.
Self multi-head attention improves speaker recognition for long utterances.
problem Speaker recognition for long speech segments using Deep Learning.
method Convolutional Neural Network (CNN) for short-term features, self multi-head attention for long-term embeddings.
result Self multi-head attention outperforms other pooling methods by 18% relative EER on VoxCeleb1 dataset.
We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedd…
Although highly correlated, speech and speaker recognition have been regarded as two independent tasks and studied by two communities. This is certainly not the way that people behave: we decipher both speech content and speaker traits at the same time. This paper presents a unified model to perform speech and speaker …
Improved multi-user VoiceFilter-Lite model for speech recognition.
problem Limited performance of multi-user VoiceFilter-Lite models.
method Dual learning rate schedule and FiLM for feature conditioning.
result Closed the performance gap between multi-user and single-user VoiceFilter-Lite models.
Improved SincNet for better speaker recognition.
problem Speaker recognition challenges and the need for better deep learning models.
method Proposes AM-SincNet, a SincNet-based model with an improved AM-Softmax layer.
result Improved speaker recognition performance, achieving a 40% Frame Error Rate reduction.
End-to-end speaker verification framework reduces text dependency.
problem Improving text-independent speaker verification.
method Jointly trains SE and ASR networks with triplet loss and adversarial gradient.
result Lower equal error rate and better text-independency compared to other approaches.
This paper presents the Intelligent Voice (IV) system submitted to the NIST 2016 Speaker Recognition Evaluation (SRE). The primary emphasis of SRE this year was on developing speaker recognition technology which is robust for novel languages that are much more heterogeneous than those used in the current state-of-the-a…
Bayesian approach improves speech recognition with limited speaker data.
problem Reduces mismatch between training and evaluation data due to speaker differences.
method Bayesian learning for DNN adaptation models with limited speaker data.
result Bayesian adaptation consistently outperforms deterministic methods, reducing word error rates up to 1.4%.
Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal is speaker prediction; we expect a performance improvement with this joint traini…
A new method for speaker recognition on hyperspheres improves on PLDA's limitations.
problem Improving speaker recognition on hyperspheres with PLDA's limitations.
method Probabilistic Spherical Discriminant Analysis (PSDA) using Von Mises-Fisher distributions.
result PSDA scores are closed-form and can handle various trials, improving over PLDA.
T-PSDA improves speaker recognition accuracy on toroidal submanifolds.
problem Improving speaker recognition accuracy on hypersphere embeddings.
method Extends PSDA to model within and between-speaker variabilities in toroidal submanifolds of the hypersphere.
result T-PSDA achieves accuracy on par with cosine scoring on VoxCeleb and large accuracy gains on NIST SRE'21.
Speech enhancement improved by adapting to unknown speakers without auxiliary signals.
problem Improving speech enhancement accuracy for unknown speakers.
method Adopting multi-task learning for speech enhancement and speaker identification, using multi-head self-attention.
result Achieved state-of-the-art performance and improved subjective quality.
A new framework for real-time multi-speaker diarization without prior registration.
problem Real-time multi-speaker diarization without prior registration and pretraining.
method Semi-supervised and self-supervised learning methods applied to a new benchmark.
result Robust performance in the online MiniVox framework.
WEEND uses a neural network to recognize speech and assign speakers to words.
problem End-to-end neural diarization without additional ASR and orchestration.
method Multi-task learning with an auxiliary network for ASR and speaker diarization.
result WEEND outperforms turn-based diarization and can handle 5-minute audio.
Mobile training improves speech recognition for users with unique speech characteristics.
problem Limited generalization of speaker-independent speech recognition models for users with very different speech characteristics.
method Securely training personalized end-to-end speech recognition models on mobile devices, splitting gradient computation to reduce memory usage.
result On-device personalization achieved 58.1% relative word error rate reduction compared to 63.7% in a server environment, with 18.7% performance degradation.
Improved speech recognition with cumulative adaptation methods.
problem Robust speech recognition in varying environments and speakers.
method Used a bidirectional LSTM neural network and i-vectors for adaptation.
result Achieved 13% relative improvement in word error rate.
NIST's CTS Challenge evaluates speaker recognition using telephony data.
problem Improving speaker recognition accuracy using telephony data.
method Large-scale neural network architectures, extensive data augmentation, proprietary data, and fine-tuning.
result Remarkable improvements in speaker recognition performance.
Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have required additional training data such as isolated source signals or senone alignments…
Study improves speaker verification accuracy using angular based embedding learning.
problem Improving discriminative power of embeddings for open-set speaker verification.
method Optimizes angular distance and adds margin penalty, applying various angular margin embedding strategies and proposing inter-class regularization.
result Achieved impressive results with 16.5% improvement in EER and 18.2% improvement in minimum detection cost function.
Convolutional network converts speaker voices without text.
problem Speaker conversion without text-based methods.
method Fully convolutional wav-to-wav network with ASR pre-training.
result Successfully converts TTS robot's voice to narrated audiobook voices.
We present the recent advances along with an error analysis of the IBM speaker recognition system for conversational speech. Some of the key advancements that contribute to our system include: a nearest-neighbor discriminant analysis (NDA) approach (as opposed to LDA) for intersession variability compensation in the i-…
RoyalFlush system improves multi-speaker ASR in M2MeT challenge.
problem Improving multi-speaker automatic speech recognition in noisy environments.
method Front-end processing with WPE and beamforming, data augmentation, and fusion of two ASR models.
result 12.22% absolute CER reduction on validation set and 12.11% on test set compared to baseline.
Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire length of an input sequence. In this paper, we analyze the usage of attention mec…
In this paper we study speaker linking (a.k.a.\ partitioning) given constraints of the distribution of speaker identities over speech recordings. Specifically, we show that the intractable partitioning problem becomes tractable when the constraints pre-partition the data in smaller cliques with non-overlapping speakers…
ASA improves ASR by adapting SD models to SI model's deep feature distribution.
problem Improving ASR performance on new speakers with limited data.
method Adversarial learning to regularize SD model's deep features to match SI model's.
result ASA achieves significant word error rate improvements over SI models.
Improved robustness in ASR systems with speaker adaptation.
problem Improving robustness in automatic speech recognition systems.
method Weighted-Simple-Add method for adding weighted speaker information vectors to the conformer-based acoustic model.
result Achieved 11% relative improvement in WER on Switchboard 300h Hub5'00 dataset.
Adversarial ASV improves speaker verification robustness.
problem Mismatches in training, enrollment, and test conditions degrade deep speaker embeddings.
method Adversarial multi-task training to learn condition-invariant embeddings.
result 8.8% and 14.5% relative EER improvements for known and unknown conditions.
Paper improves speaker verification with federated learning and differential privacy.
problem Improving speaker verification accuracy using private data.
method Combining federated learning and differential privacy to train an auxiliary model that predicts vocal characteristics.
result 6% relative improvement in equal error rate over a baseline system.
Paper proposes LSTM for speaker similarity measurement and improves diarization accuracy.
problem Improving speaker diarization accuracy using neural networks.
method Uses Bi-LSTM for similarity measurement and spectral clustering for clustering.
result Significantly outperforms state-of-the-art methods with diarization error rate of 6.63%.
We consider technology-assisted mimicry attacks in the context of automatic speaker verification (ASV). We use ASV itself to select targeted speakers to be attacked by human-based mimicry. We recorded 6 naive mimics for whom we select target celebrities from VoxCeleb1 and VoxCeleb2 corpora (7,365 potential targets) usi…
State-of-the-art speaker recognition systems comprise an x-vector (or i-vector) speaker embedding front-end followed by a probabilistic linear discriminant analysis (PLDA) backend. The effectiveness of these components relies on the availability of a large collection of labeled training data. In practice, it is common …
CAT is a new ASR toolkit using CRF and CTC for state-of-the-art speech recognition.
problem Improving automatic speech recognition systems.
method CRF-based discriminative training with CTC-inspired state topology.
result CAT achieves state-of-the-art results with fewer parameters and is competitive with hybrid models.
Reinterprets DNF as a deep generative LDA model for complex data.
problem Limited applicability of LDA in complex data scenarios.
method Proposes a discriminative normalization flow (DNF) model and interprets it as a deep generative LDA.
result DNF and its subspace version outperform conventional LDA in modeling complex data.