1.8k citations · 3.5k across the 130 of their papers we have counts for
27 papers · 1 filter
Detecting and Correcting Adversarial Images Using Image Processing Operations
Huy H. Nguyen, Minoru Kuribayashi, Junichi Yamagishi +1
Deep neural networks (DNNs) have achieved excellent performance on several tasks and have been widely applied in both academia and industry. However, DNNs are vulnerable to adversa…
Transformation of low-quality device-recorded speech to high-quality speech using improved SEGAN model
Seyyed Saeed Sarfjoo, Xin Wang, Gustav Eje Henter +3
Nowadays vast amounts of speech data are recorded from low-quality recorder devices such as smartphones, tablets, laptops, and medium-quality microphones. The objective of this res…
Transferring neural speech waveform synthesizers to musical instrument sounds generation
Yi Zhao, Xin Wang, Lauri Juvela +1
Recent neural waveform synthesizers such as WaveNet, WaveGlow, and the neural-source-filter (NSF) model have shown good performance in speech synthesis despite their different meth…
A Method for Identifying Origin of Digital Images Using a Convolution Neural Network
Rong Huang, Fuming Fang, Huy H. Nguyen +2
The rapid development of deep learning techniques has created new challenges in identifying the origin of digital images because generative adversarial networks and variational aut…
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Xin Wang, Junichi Yamagishi, Massimiliano Todisco +37
Automatic speaker verification (ASV) is one of the most natural and convenient means of biometric person recognition. Unfortunately, just like all other biometric systems, ASV is v…
Security of Facial Forensics Models Against Adversarial Attacks
Rong Huang, Fuming Fang, Huy H. Nguyen +2
Deep neural networks (DNNs) have been used in digital forensics to identify fake facial images. We investigated several DNN-based forgery forensics models (FFMs) to examine whether…
Modeling of Rakugo Speech and Its Limitations: Toward Speech Synthesis That Entertains Audiences
Shuhei Kato, Yusuke Yasuda, Xin Wang +3
We have been investigating rakugo speech synthesis as a challenging example of speech synthesis that entertains audiences. Rakugo is a traditional Japanese form of verbal entertain…
Use of a Capsule Network to Detect Fake Images and Videos
Huy H. Nguyen, Junichi Yamagishi, Isao Echizen
The revolution in computer hardware, especially in graphics processing units and tensor processing units, has enabled significant advances in computer graphics and artificial intel…
Effect of choice of probability distribution, randomness, and search methods for alignment modeling in sequence-to-sequence text-to-speech synthesis using hard alignment
Yusuke Yasuda, Xin Wang, Junichi Yamagishi
Sequence-to-sequence text-to-speech (TTS) is dominated by soft-attention-based methods. Recently, hard-attention-based methods have been proposed to prevent fatal alignment errors,…
Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings
Erica Cooper, Cheng-I Lai, Yusuke Yasuda +4
While speaker adaptation for end-to-end speech synthesis using speaker embeddings can produce good speaker similarity for speakers seen during training, there remains a gap for zer…
Bootstrapping non-parallel voice conversion from speaker-adaptive text-to-speech
Hieu-Thi Luong, Junichi Yamagishi
Voice conversion (VC) and text-to-speech (TTS) are two tasks that share a similar objective, generating speech with a target voice. However, they are usually developed independentl…
Initial investigation of an encoder-decoder end-to-end TTS framework using marginalization of monotonic hard latent alignments
Yusuke Yasuda, Xin Wang, Junichi Yamagishi
End-to-end text-to-speech (TTS) synthesis is a method that directly converts input text to output acoustic features using a single network. A recent advance of end-to-end TTS is du…
Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis
Xin Wang, Junichi Yamagishi
Neural source-filter (NSF) models are deep neural networks that produce waveforms given input acoustic features. They use dilated-convolution-based neural filter modules to filter…
Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection
David Ifeoluwa Adelani, Haotian Mai, Fuming Fang +3
Advanced neural language models (NLMs) are widely used in sequence generation tasks because they are able to produce fluent and meaningful sentences. They can also be used to gener…
Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videos
Huy H. Nguyen, Fuming Fang, Junichi Yamagishi +1
Detecting manipulated images and videos is an important topic in digital media forensics. Most detection methods use binary classification to determine the probability of a query b…
A Unified Speaker Adaptation Method for Speech Synthesis using Transcribed and Untranscribed Speech with Backpropagation
Hieu-Thi Luong, Junichi Yamagishi
By representing speaker characteristic as a single fixed-length vector extracted solely from speech, we can train a neural multi-speaker speech synthesis model by conditioning the…
Speaker Anonymization Using X-vector and Neural Waveform Models
Fuming Fang, Xin Wang, Junichi Yamagishi +4
The social media revolution has produced a plethora of web services to which users can easily upload and share multimedia documents. Despite the popularity and convenience of such…
ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
Massimiliano Todisco, Xin Wang, Ville Vestman +7
ASVspoof, now in its third edition, is a series of community-led challenges which promote the development of countermeasures to protect automatic speaker verification (ASV) from th…
Does the Lombard Effect Improve Emotional Communication in Noise? - Analysis of Emotional Speech Acted in Noise -
Yi Zhao, Atsushi Ando, Shinji Takaki +2
Speakers usually adjust their way of talking in noisy environments involuntarily for effective communication. This adaptation is known as the Lombard effect. Although speech accomp…
Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora
Hieu-Thi Luong, Xin Wang, Junichi Yamagishi +1
When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers…
Training a Neural Speech Waveform Model using Spectral Losses of Short-Time Fourier Transform and Continuous Wavelet Transform
Shinji Takaki, Hirokazu Kameoka, Junichi Yamagishi
Recently, we proposed short-time Fourier transform (STFT)-based loss functions for training a neural speech waveform model. In this paper, we generalize the above framework and pro…
Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNet
Mingyang Zhang, Xin Wang, Fuming Fang +2
We investigated the training of a shared model for both text-to-speech (TTS) and voice conversion (VC) tasks. We propose using an extended model architecture of Tacotron, that is a…
Neural source-filter waveform models for statistical parametric speech synthesis
Xin Wang, Shinji Takaki, Junichi Yamagishi
Neural waveform models such as WaveNet have demonstrated better performance than conventional vocoders for statistical parametric speech synthesis. As an autoregressive (AR) model,…
MOSNet: Deep Learning based Objective Assessment for Voice Conversion
Chen-Chou Lo, Szu-Wei Fu, Wen-Chin Huang +4
Existing objective evaluation metrics for voice conversion (VC) are not always correlated with human perception. Therefore, training VC models with such criteria may not effectivel…