175 citations · 709 across the 60 of their papers we have counts for
40 papers · 1 filter
ROAR: Reinforcing Original to Augmented Data Ratio Dynamics for Wav2Vec2.0 Based ASR
Vishwanath Pratap Singh, Federico Malato, Ville Hautamaki +2
While automatic speech recognition (ASR) greatly benefits from data augmentation, the augmentation recipes themselves tend to be heuristic. In this paper, we address one of the heu…
Revisiting and Improving Scoring Fusion for Spoofing-aware Speaker Verification Using Compositional Data Analysis
Xin Wang, Tomi Kinnunen, Kong Aik Lee +2
Fusing outputs from automatic speaker verification (ASV) and spoofing countermeasure (CM) is expected to make an integrated system robust to zero-effort imposters and synthesized s…
ChildAugment: Data Augmentation Methods for Zero-Resource Children's Speaker Verification
Vishwanath Pratap Singh, Md Sahidullah, Tomi Kinnunen
The accuracy of modern automatic speaker verification (ASV) systems, when trained exclusively on adult data, drops substantially when applied to children's speech. The scarcity of…
Speaker Verification Across Ages: Investigating Deep Speaker Embedding Sensitivity to Age Mismatch in Enrollment and Test Speech
Vishwanath Pratap Singh, Md Sahidullah, Tomi Kinnunen
In this paper, we study the impact of the ageing on modern deep speaker embedding based automatic speaker verification (ASV) systems. We have selected two different datasets to exa…
Towards single integrated spoofing-aware speaker verification embeddings
Sung Hwan Mun, Hye-jin Shim, Hemlata Tak +12
This study aims to develop a single integrated spoofing-aware speaker verification (SASV) embeddings that satisfy two aspects. First, rejecting non-target speakers' input as well a…
Learnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation
Mark Anderson, Tomi Kinnunen, Naomi Harte
While much of modern speech and audio processing relies on deep neural networks trained using fixed audio representations, recent studies suggest great potential in acoustic fronte…
I4U System Description for NIST SRE'20 CTS Challenge
Kong Aik Lee, Tomi Kinnunen, Daniele Colibro +23
This manuscript describes the I4U submission to the 2020 NIST Speaker Recognition Evaluation (SRE'20) Conversational Telephone Speech (CTS) Challenge. The I4U's submission was resu…
An Initial study on Birdsong Re-synthesis Using Neural Vocoders
Rhythm Bhatia, Tomi H. Kinnunen
Modern speech synthesis uses neural vocoders to model raw waveform samples directly. This increased versatility has expanded the scope of vocoders from speech to other domains, suc…
Baselines and Protocols for Household Speaker Recognition
Alexey Sholokhov, Xuechen Liu, Md Sahidullah +1
Speaker recognition on household devices, such as smart speakers, features several challenges: (i) robustness across a vast number of heterogeneous domains (households), (ii) short…
SASV 2022: The First Spoofing-Aware Speaker Verification Challenge
Jee-weon Jung, Hemlata Tak, Hye-jin Shim +6
The first spoofing-aware speaker verification (SASV) challenge aims to integrate research efforts in speaker verification and anti-spoofing. We extend the speaker verification scen…
ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
Junichi Yamagishi, Xin Wang, Massimiliano Todisco +8
ASVspoof 2021 is the forth edition in the series of bi-annual challenges which aim to promote the study of spoofing and the design of countermeasures to protect automatic speaker v…
ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan
Héctor Delgado, Nicholas Evans, Tomi Kinnunen +8
The automatic speaker verification spoofing and countermeasures (ASVspoof) challenge series is a community-led initiative which aims to promote the consideration of spoofing and th…
Data Quality as Predictor of Voice Anti-Spoofing Generalization
Bhusan Chettri, Rosa González Hautamäki, Md Sahidullah +1
Voice anti-spoofing aims at classifying a given utterance either as a bonafide human sample, or a spoofing attack (e.g. synthetic or replayed sample). Many anti-spoofing methods ha…
ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech
Andreas Nautsch, Xin Wang, Nicholas Evans +7
The ASVspoof initiative was conceived to spearhead research in anti-spoofing for automatic speaker verification (ASV). This paper describes the third in a series of bi-annual chall…
Predictions of Subjective Ratings and Spoofing Assessments of Voice Conversion Challenge 2020 Submissions
Rohan Kumar Das, Tomi Kinnunen, Wen-Chin Huang +5
The Voice Conversion Challenge 2020 is the third edition under its flagship that promotes intra-lingual semiparallel and cross-lingual voice conversion (VC). While the primary eval…
Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion
Yi Zhao, Wen-Chin Huang, Xiaohai Tian +5
The voice conversion challenge is a bi-annual scientific event held to compare and understand different voice conversion (VC) systems built on a common dataset. In 2020, we organiz…
Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals
Tomi Kinnunen, Héctor Delgado, Nicholas Evans +8
Recent years have seen growing efforts to develop spoofing countermeasures (CMs) to protect automatic speaker verification (ASV) systems from being deceived by manipulated or artif…
Why Did the x-Vector System Miss a Target Speaker? Impact of Acoustic Mismatch Upon Target Score on VoxCeleb Data
Rosa González Hautamäki, Tomi Kinnunen
Modern automatic speaker verification (ASV) relies heavily on machine learning implemented through deep neural networks. It can be difficult to interpret the output of these black…
Extrapolating false alarm rates in automatic speaker verification
Alexey Sholokhov, Tomi Kinnunen, Ville Vestman +1
Automatic speaker verification (ASV) vendors and corpus providers would both benefit from tools to reliably extrapolate performance metrics for large speaker populations without co…
A Comparative Re-Assessment of Feature Extractors for Deep Speaker Embeddings
Xuechen Liu, Md Sahidullah, Tomi Kinnunen
Modern automatic speaker verification relies largely on deep neural networks (DNNs) trained on mel-frequency cepstral coefficient (MFCC) features. While there are alternative featu…
UIAI System for Short-Duration Speaker Verification Challenge 2020
Md Sahidullah, Achintya Kumar Sarkar, Ville Vestman +5
In this work, we present the system description of the UIAI entry for the short-duration speaker verification (SdSV) challenge 2020. Our focus is on Task 1 dedicated to text-depend…
The Attacker's Perspective on Automatic Speaker Verification: An Overview
Rohan Kumar Das, Xiaohai Tian, Tomi Kinnunen +1
Security of automatic speaker verification (ASV) systems is compromised by various spoofing attacks. While many types of non-proactive attacks (and their defenses) have been studie…
Neural i-vectors
Ville Vestman, Kong Aik Lee, Tomi H. Kinnunen
Deep speaker embeddings have been demonstrated to outperform their generative counterparts, i-vectors, in recent speaker verification evaluations. To combine the benefits of high p…
Subband modeling for spoofing detection in automatic speaker verification
Bhusan Chettri, Tomi Kinnunen, Emmanouil Benetos
Spectrograms - time-frequency representations of audio signals - have found widespread use in neural network-based spoofing detection. While deep models are trained on the fullband…