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.
SpeakerStew verifies 46 languages with reduced training and inference costs.
problem Speaker verification for 46 languages with smart speaker interactions.
method Pooling multilingual data, triage between text-dependent and text-independent models.
result Training on multiple languages generalizes well and reduces computational requirements.
Proposes SPE for robust speaker verification.
problem Improving text-independent speaker verification accuracy.
method Spatial pyramid encoding and deep length normalization.
result Proposed system outperforms i-vector and d-vector baselines.
Recent speech technology research has seen a growing interest in using WaveNets as statistical vocoders, i.e., generating speech waveforms from acoustic features. These models have been shown to improve the generated speech quality over classical vocoders in many tasks, such as text-to-speech synthesis and voice conver…
We propose an algorithm to separate simultaneously speaking persons from each other, the "cocktail party problem", using a single microphone. Our approach involves a deep recurrent neural networks regression to a vector space that is descriptive of independent speakers. Such a vector space can embed empirically determi…
Standard probabilistic linear discriminant analysis (PLDA) for speaker recognition assumes that the sample's features (usually, i-vectors) are given by a sum of three terms: a term that depends on the speaker identity, a term that models the within-speaker variability and is assumed independent across samples, and a fi…
We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of training is not to produce a neural network with fixed weights, which is then deplo…
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 …
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.
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.
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…
This paper presents a self-supervised method for visual detection of the active speaker in a multi-person spoken interaction scenario. Active speaker detection is a fundamental prerequisite for any artificial cognitive system attempting to acquire language in social settings. The proposed method is intended to compleme…
Seq2seq ASR adapts to speakers, improving performance by 25%.
problem Speaker adaptation for seq2seq ASR systems to match conventional methods.
method Applied Kullback-Leibler divergence and Linear Hidden Network adaptation to seq2seq models.
result 25% relative word error rate improvement with seq2seq model adaptation.
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.
An important step in speaker verification is extracting features that best characterize the speaker voice. This paper investigates a front-end processing that aims at improving the performance of speaker verification based on the SVMs classifier, in text independent mode. This approach combines features based on conven…
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.
Paper extends ICA to ISA with auxiliary variables for better speech representation learning.
problem Learning unsupervised speech representations with independent subspaces.
method Theoretical framework of nonlinear ISA with auxiliary variables.
result Proposes an algorithm to learn speech representations with independent subspaces.
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.
A novel text-independent speaker identification (SI) method is proposed. This method uses the Mel-frequency Cepstral coefficients (MFCCs) and the dynamic information among adjacent frames as feature sets to capture speaker's characteristics. In order to utilize dynamic information, we design super-MFCCs features by cas…
Improved visual speech synthesis using adapted ASR acoustic models.
problem Lack of synchronized audio, video, and depth data for speaker-independent speech-driven visual speech synthesis.
method Adapted an ASR acoustic model trained on audio-only data to the visual speech synthesis domain.
result Viewers significantly prefer animations generated from the adapted ASR acoustic model.
Deep clustering is a recently introduced deep learning architecture that uses discriminatively trained embeddings as the basis for clustering. It was recently applied to spectrogram segmentation, resulting in impressive results on speaker-independent multi-speaker separation. In this paper we extend the baseline system…
Hybrid diarization framework handles overlapped speech and long recordings.
problem Challenges in clustering-based and end-to-end neural diarization approaches.
method Proposes a hybrid framework combining clustering and end-to-end neural diarization.
result Significantly better performance on long recordings with overlapped speech.
Proposes DNN-based speaker embedding correlated with subjective inter-speaker similarity for speech synthesis.
problem Inadequate speaker representation for open speakers not in training data.
method Two training algorithms using inter-speaker similarity matrices: similarity vector embedding and similarity matrix embedding.
result Proposed algorithms learn speaker embedding highly correlated with subjective inter-speaker similarity.
Combining data from multiple speakers improves neural TTS quality, especially with imbalanced data.
problem Training high-quality TTS systems with imbalanced speaker data.
method Combine data from multiple speakers, train multi-speaker models, and use ensemble methods.
result Ensemble multi-speaker models improve synthetic speech quality for underrepresented speakers.
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) …
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.
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.
Graph neural networks refine speaker embeddings for better session-level diarization.
problem Local speaker distinction in meeting sessions using deep embeddings.
method Graph Neural Networks (GNNs) refine speaker embeddings using session-level structural information.
result Spectral clustering on refined embeddings outperforms original embeddings significantly.
We address the problem of acoustic source separation in a deep learning framework we call "deep clustering." Rather than directly estimating signals or masking functions, we train a deep network to produce spectrogram embeddings that are discriminative for partition labels given in training data. Previous deep network …
Improved neural speaker embeddings enhance ASR performance.
problem Few studies have explored neural speaker embeddings for ASR.
method Integrating improved neural speaker embeddings into a conformer-based hybrid HMM ASR system.
result Improved neural embeddings achieve on-par performance with i-vectors.
We present a factorized hierarchical variational autoencoder, which learns disentangled and interpretable representations from sequential data without supervision. Specifically, we exploit the multi-scale nature of information in sequential data by formulating it explicitly within a factorized hierarchical graphical mo…
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.
Anonymizes speech data to protect privacy.
problem Protecting personal speech data from misuse.
method Extracts features, uses x-vectors, and neural models to synthesize anonymized speech.
result Effective in concealing speaker identities without compromising speech quality.
This paper proposes a new architecture for speaker adaptation of multi-speaker neural-network speech synthesis systems, in which an unseen speaker's voice can be built using a relatively small amount of speech data without transcriptions. This is sometimes called "unsupervised speaker adaptation". More specifically, we…
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.
Paper explores using EEG for better speaker identification, even in noisy environments.
problem Speaker identification performance degrades in background noise.
method Uses EEG signals to enhance speaker identification systems, comparing with acoustic features.
result Speaker identification system using only EEG features outperforms one using only acoustic features in high background noise.
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.
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.
A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown promising results. The extracted frame-level (DNN bottleneck, posterior or d-vector) …
New models extrapolate false alarms in ASV without new data.
problem Reliable extrapolation of false alarm rates in ASV without new speaker data.
method Generative models in ASV score space for arbitrary systems.
result Models accurately extrapolate false alarm rates for large speaker populations.
Improves speaker verification for variable-duration utterances using a feature pyramid module.
problem Improving robustness for variable-duration utterances in speaker verification.
method Integrates a feature pyramid module into multi-scale aggregation to enhance speaker-discriminative information from multiple layers.
result Improves performance for both short and long utterances compared to state-of-the-art approaches.
Conditional T/S learning improves student model performance by selectively learning from teacher or ground truth.
problem Teacher's occasional wrong guidance leads to suboptimal student model performance.
method Proposes a conditional T/S learning scheme where the student selectively chooses between teacher and ground truth based on teacher correctness.
result The conditional learning achieves significant performance improvements over traditional T/S learning.
EEG signals enhance speaker verification system robustness.
problem Improving speaker verification in noisy environments.
method Used end-to-end deep learning model with EEG and speech features.
result EEG signals improve speaker verification robustness, especially in noisy conditions.
BOFFIN TTS optimizes hyper-parameters for new speaker adaptation.
problem Fine-tuning a pre-trained TTS model for a new speaker with limited data.
method Bayesian optimization to efficiently find optimal hyper-parameters.
result Average 30% improvement in speaker similarity over standard techniques.
New method separates multiple voices in mixed audio.
problem Separating multiple simultaneous speakers in audio.
method Gated neural networks trained at multiple steps, selecting actual number of speakers.
result Outperforms current state of the art for more than two speakers.
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.
Speaker verification (SV) systems using deep neural network embeddings, so-called the x-vector systems, are becoming popular due to its good performance superior to the i-vector systems. The fusion of these systems provides improved performance benefiting both from the discriminatively trained x-vectors and generative …