Search Results for author:
Found 37 papers, 10 papers with code
A Randomized Link Transformer for Diverse Open-Domain Dialogue Generation
A major issue in open-domain dialogue generation is the agent’s tendency to generate repetitive and generic responses.
Generalized domain adaptation framework for parametric back-end in speaker recognition
The efficacy of the proposed techniques has been experimentally validated on NIST 2016, 2018, and 2019 Speaker Recognition Evaluation (SRE'16, SRE'18, and SRE'19) datasets.
Incorporating Uncertainty from Speaker Embedding Estimation to Speaker Verification
We propose a log-likelihood ratio function for the PLDA scoring with the uncertainty propagation.
Cross-modal Audio-visual Co-learning for Text-independent Speaker Verification
Visual speech (i. e., lip motion) is highly related to auditory speech due to the co-occurrence and synchronization in speech production.
Probabilistic Back-ends for Online Speaker Recognition and Clustering
This paper focuses on multi-enrollment speaker recognition which naturally occurs in the task of online speaker clustering, and studies the properties of different scoring back-ends in this scenario.
I4U System Description for NIST SRE'20 CTS Challenge
This manuscript describes the I4U submission to the 2020 NIST Speaker Recognition Evaluation (SRE'20) Conversational Telephone Speech (CTS) Challenge.
Speaker recognition with two-step multi-modal deep cleansing
However, noisy samples (i. e., with wrong labels) in the training set induce confusion and cause the network to learn the incorrect representation.
Self-Supervised Training of Speaker Encoder with Multi-Modal Diverse Positive Pairs
We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels.
Deep Spectro-temporal Artifacts for Detecting Synthesized Speech
The Audio Deep Synthesis Detection (ADD) Challenge has been held to detect generated human-like speech.
The Conversational Short-phrase Speaker Diarization (CSSD) Task: Dataset, Evaluation Metric and Baselines
In the metric aspect, we design the new conversational DER (CDER) evaluation metric, which calculates the SD accuracy at the utterance level.
Scoring of Large-Margin Embeddings for Speaker Verification: Cosine or PLDA?
The emergence of large-margin softmax cross-entropy losses in training deep speaker embedding neural networks has triggered a gradual shift from parametric back-ends to a simpler cosine similarity measure for speaker verification.
Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents
Empirical results show that our framework significantly improves the contextual coherence of the generated response.
MFA: TDNN with Multi-scale Frequency-channel Attention for Text-independent Speaker Verification with Short Utterances
The time delay neural network (TDNN) represents one of the state-of-the-art of neural solutions to text-independent speaker verification.
DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation
The generation of personalized dialogue is vital to natural and human-like conversation.
Self-supervised Speaker Recognition with Loss-gated Learning
In self-supervised learning for speaker recognition, pseudo labels are useful as the supervision signals.
PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction
Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise.
ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan
The automatic speaker verification spoofing and countermeasures (ASVspoof) challenge series is a community-led initiative which aims to promote the consideration of spoofing and the development of countermeasures.
ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
In addition to a continued focus upon logical and physical access tasks in which there are a number of advances compared to previous editions, ASVspoof 2021 introduces a new task involving deepfake speech detection.
Task-aware Warping Factors in Mask-based Speech Enhancement
It is easy to apply the proposed dual-warping factors approach to any mask-based SE method, and it allows a single SE system to handle multiple tasks without task-dependent training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Xi-Vector Embedding for Speaker Recognition
We present a Bayesian formulation for deep speaker embedding, wherein the xi-vector is the Bayesian counterpart of the x-vector, taking into account the uncertainty estimate.
Generating Personalized Dialogue via Multi-Task Meta-Learning
To address these practical limitations, we propose a novel multi-task meta-learning approach which involves training a model to adapt to new personas without relying on a large corpus, or on any predefined persona information.
Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
Instead of utilizing multi-head attention in parallel, the proposed serialized multi-layer multi-head attention is designed to aggregate and propagate attentive statistics from one layer to the next in a serialized manner.
Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing
Whether it be for results summarization, or the analysis of classifier fusion, some means to compare different classifiers can often provide illuminating insight into their behaviour, (dis)similarity or complementarity.
Exploring Deep Learning for Joint Audio-Visual Lip Biometrics
Audio-visual (AV) lip biometrics is a promising authentication technique that leverages the benefits of both the audio and visual modalities in speech communication.
ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech
The ASVspoof initiative was conceived to spearhead research in anti-spoofing for automatic speaker verification (ASV).
Extrapolating false alarm rates in automatic speaker verification
Automatic speaker verification (ASV) vendors and corpus providers would both benefit from tools to reliably extrapolate performance metrics for large speaker populations without collecting new speakers.
Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals
Recent years have seen growing efforts to develop spoofing countermeasures (CMs) to protect automatic speaker verification (ASV) systems from being deceived by manipulated or artificial inputs.
Neural i-vectors
To combine the benefits of high performance and generative interpretation, we investigate the use of deep embedding extractor and i-vector extractor in succession.
Short-duration Speaker Verification (SdSV) Challenge 2021: the Challenge Evaluation Plan
This document describes the Short-duration Speaker Verification (SdSV) Challenge 2021.
Speaker detection in the wild: Lessons learned from JSALT 2019
This paper presents the problems and solutions addressed at the JSALT workshop when using a single microphone for speaker detection in adverse scenarios.
Audio and Speech Processing Sound
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Spoofing attacks within a logical access (LA) scenario are generated with the latest speech synthesis and voice conversion technologies, including state-of-the-art neural acoustic and waveform model techniques.
Voice Biometrics Security: Extrapolating False Alarm Rate via Hierarchical Bayesian Modeling of Speaker Verification Scores
We put forward a novel performance assessment framework to address both the inadequacy of the random-impostor evaluation model and the size limitation of evaluation corpora by addressing ASV security against closest impostors on arbitrarily large datasets.
Unleashing the Unused Potential of I-Vectors Enabled by GPU Acceleration
In particular, we achieve an acceleration of 3000 times in frame posterior computation compared to real time and 25 times in training the i-vector extractor compared to the CPU baseline from Kaldi toolkit.
I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences
The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE).
The CORAL+ Algorithm for Unsupervised Domain Adaptation of PLDA
We refer to the model-based adaptation technique proposed in this paper as CORAL+.
t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification
The two challenge editions in 2015 and 2017 involved the assessment of spoofing countermeasures (CMs) in isolation from ASV using an equal error rate (EER) metric.
Fantastic 4 system for NIST 2015 Language Recognition Evaluation
This article describes the systems jointly submitted by Institute for Infocomm (I$^2$R), the Laboratoire d'Informatique de l'Universit\'e du Maine (LIUM), Nanyang Technology University (NTU) and the University of Eastern Finland (UEF) for 2015 NIST Language Recognition Evaluation (LRE).
