Search Results for author:
Found 36 papers, 13 papers with code
Adapting Language Models When Training on Privacy-Transformed Data
In recent years, voice-controlled personal assistants have revolutionized the interaction with smart devices and mobile applications.
Transformer versus LSTM Language Models trained on Uncertain ASR Hypotheses in Limited Data Scenarios
Training of LSTM LMs in such limited data scenarios can benefit from alternate uncertain ASR hypotheses, as observed in our recent work.
Analysis of Speech Temporal Dynamics in the Context of Speaker Verification and Voice Anonymization
In this paper, we investigate the impact of speech temporal dynamics in application to automatic speaker verification and speaker voice anonymization tasks.
Joint Beamforming and Speaker-Attributed ASR for Real Distant-Microphone Meeting Transcription
Distant-microphone meeting transcription is a challenging task.
The First VoicePrivacy Attacker Challenge Evaluation Plan
Results will be presented at the ICASSP 2025 special session to which 5 selected top-ranked participants will be invited to submit and present their challenge systems.
The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation
The VoicePrivacy Challenge promotes the development of voice anonymisation solutions for speech technology.
The VoicePrivacy 2024 Challenge Evaluation Plan
The task of the challenge is to develop a voice anonymization system for speech data which conceals the speaker's voice identity while protecting linguistic content and emotional states.
Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications
Past studies on end-to-end meeting transcription have focused on model architecture and have mostly been evaluated on simulated meeting data.
End-to-end Joint Punctuated and Normalized ASR with a Limited Amount of Punctuated Training Data
We propose two approaches to train an end-to-end joint punctuated and normalized ASR system using limited punctuated data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis
We present an end-to-end multichannel speaker-attributed automatic speech recognition (MC-SA-ASR) system that combines a Conformer-based encoder with multi-frame crosschannel attention and a speaker-attributed Transformer-based decoder.
Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS
Flow-based generative models are widely used in text-to-speech (TTS) systems to learn the distribution of audio features (e. g., Mel-spectrograms) given the input tokens and to sample from this distribution to generate diverse utterances.
Can we use Common Voice to train a Multi-Speaker TTS system?
We show the viability of this approach for training a multi-speaker GlowTTS model on the Common Voice English dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
The VoicePrivacy 2020 Challenge Evaluation Plan
The VoicePrivacy Challenge aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges.
The VoicePrivacy 2022 Challenge Evaluation Plan
Participants apply their developed anonymization systems, run evaluation scripts and submit objective evaluation results and anonymized speech data to the organizers.
Differentially Private Speaker Anonymization
We remove speaker information from these attributes by introducing differentially private feature extractors based on an autoencoder and an automatic speech recognizer, respectively, trained using noise layers.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
The VoicePrivacy 2020 Challenge: Results and findings
We provide a systematic overview of the challenge design with an analysis of submitted systems and evaluation results.
Blind Room Parameter Estimation Using Multiple-Multichannel Speech Recordings
Knowing the geometrical and acoustical parameters of a room may benefit applications such as audio augmented reality, speech dereverberation or audio forensics.
UIAI System for Short-Duration Speaker Verification Challenge 2020
Our primary submission to the challenge is the fusion of seven subsystems which yields a normalized minimum detection cost function (minDCF) of 0. 072 and an equal error rate (EER) of 2. 14% on the evaluation set.
LibriMix: An Open-Source Dataset for Generalizable Speech Separation
Most deep learning-based speech separation models today are benchmarked on it.
Audio and Speech Processing
Design Choices for X-vector Based Speaker Anonymization
The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker.
Foreground-Background Ambient Sound Scene Separation
Ambient sound scenes typically comprise multiple short events occurring on top of a somewhat stationary background.
Introducing the VoicePrivacy Initiative
The VoicePrivacy initiative aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges.
CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings
Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges we organize the 6th CHiME Speech Separation and Recognition Challenge (CHiME-6).
Limitations of weak labels for embedding and tagging
Many datasets and approaches in ambient sound analysis use weakly labeled data. Weak labels are employed because annotating every data sample with a strong label is too expensive. Yet, their impact on the performance in comparison to strong labels remains unclear. Indeed, weak labels must often be dealt with at the same time as other challenges, namely multiple labels per sample, unbalanced classes and/or overlapping events. In this paper, we formulate a supervised learning problem which involves weak labels. We create a dataset that focuses on the difference between strong and weak labels as opposed to other challenges.
Joint NN-Supported Multichannel Reduction of Acoustic Echo, Reverberation and Noise
We consider the problem of simultaneous reduction of acoustic echo, reverberation and noise.
Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?
In this paper, we focus on the protection of speaker identity and study the extent to which users can be recognized based on the encoded representation of their speech as obtained by a deep encoder-decoder architecture trained for ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Evaluating Voice Conversion-based Privacy Protection against Informed Attackers
In this paper, we investigate anonymization methods based on voice conversion.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
The Speed Submission to DIHARD II: Contributions & Lessons Learned
This paper describes the speaker diarization systems developed for the Second DIHARD Speech Diarization Challenge (DIHARD II) by the Speed team.
Filterbank design for end-to-end speech separation
Also, we validate the use of parameterized filterbanks and show that complex-valued representations and masks are beneficial in all conditions.
Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition
The transcriptions used to train an Automatic Speech Recognition (ASR) system may contain errors.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
SemEval-2019 Task 4: Hyperpartisan News Detection
Hyperpartisan news is news that takes an extreme left-wing or right-wing standpoint.
AI in the media and creative industries
Thanks to the Big Data revolution and increasing computing capacities, Artificial Intelligence (AI) has made an impressive revival over the past few years and is now omnipresent in both research and industry.
A Statistically Principled and Computationally Efficient Approach to Speech Enhancement using Variational Autoencoders
Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speech enhancement.
An improved uncertainty propagation method for robust i-vector based speaker recognition
So far, different uncertainty propagation methods have been proposed to compensate noise and reverberation in i-vectors in the context of speaker recognition.
The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines
The CHiME challenge series aims to advance robust automatic speech recognition (ASR) technology by promoting research at the interface of speech and language processing, signal processing , and machine learning.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Rank-1 Constrained Multichannel Wiener Filter for Speech Recognition in Noisy Environments
Multichannel linear filters, such as the Multichannel Wiener Filter (MWF) and the Generalized Eigenvalue (GEV) beamformer are popular signal processing techniques which can improve speech recognition performance.
