50 citations · 75 across the 26 of their papers we have counts for
21 papers · 1 filter
Music Source Separation via Stem Discovery
V. Valtteri Kallinen, Eloi Moliner, Lauri Juvela +1
Music source separation (MSS) methods aim to extract stems from music mixtures, which is important, for example, in karaoke, music remixing, and pedagogical applications. While ear…
EmphTTS: an emphasis-control TTS with reinforcement learning
Zirui Li, Rech Silas, Lauri Juvela +2
Generating controllable and human-like emphasis remains an open challenge in text-to-speech, even when explicit emphasis control signals are provided in the text input, limiting th…
Music Restoration via Latent Operator Optimization and Diffusion Model Priors
Michal Švento, Eloi Moliner, Valtteri Kallinen +3
Music restoration seeks to recover a clean signal from an observed recording degraded by an unknown effect, distortion, or corruption. Existing systems often rely on paired trainin…
Nord-Parl-TTS: Finnish and Swedish TTS Dataset from Parliament Speech
Zirui Li, Jens Edlund, Yicheng Gu +3
Text-to-speech (TTS) development is limited by scarcity of high-quality, publicly available speech data for most languages outside a few high-resource languages. We present Nord-Pa…
Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams
Zirui Li, Lauri Juvela, Mikko Kurimo
Synthesizing second-language (L2) speech is potentially highly valued for L2 language learning experience and feedback. However, due to the lack of L2 speech synthesis datasets, it…
Unsupervised Estimation of Nonlinear Audio Effects: Comparing Diffusion-Based and Adversarial approaches
Eloi Moliner, Michal Švento, Alec Wright +3
Accurately estimating nonlinear audio effects without access to paired input-output signals remains a challenging problem. This work studies unsupervised probabilistic approaches f…
Estimation and Restoration of Unknown Nonlinear Distortion using Diffusion
Michal Švento, Eloi Moliner, Lauri Juvela +2
The restoration of nonlinearly distorted audio signals, alongside the identification of the applied memoryless nonlinear operation, is studied. The paper focuses on the difficult b…
Open-Amp: Synthetic Data Framework for Audio Effect Foundation Models
Alec Wright, Alistair Carson, Lauri Juvela
This paper introduces Open-Amp, a synthetic data framework for generating large-scale and diverse audio effects data. Audio effects are relevant to many musical audio processing an…
Collaborative Watermarking for Adversarial Speech Synthesis
Lauri Juvela, Xin Wang
Advances in neural speech synthesis have brought us technology that is not only close to human naturalness, but is also capable of instant voice cloning with little data, and is hi…
Speaker-independent neural formant synthesis
Pablo Pérez Zarazaga, Zofia Malisz, Gustav Eje Henter +1
We describe speaker-independent speech synthesis driven by a small set of phonetically meaningful speech parameters such as formant frequencies. The intention is to leverage deep-l…
Adversarial Guitar Amplifier Modelling With Unpaired Data
Alec Wright, Vesa Välimäki, Lauri Juvela
We propose an audio effects processing framework that learns to emulate a target electric guitar tone from a recording. We train a deep neural network using an adversarial approach…
Conditional Spoken Digit Generation with StyleGAN
Kasperi Palkama, Lauri Juvela, Alexander Ilin
This paper adapts a StyleGAN model for speech generation with minimal or no conditioning on text. StyleGAN is a multi-scale convolutional GAN capable of hierarchically capturing da…
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…
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…
GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-spectrogram
Lauri Juvela, Bajibabu Bollepalli, Junichi Yamagishi +1
Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to m…
Generative adversarial network-based glottal waveform model for statistical parametric speech synthesis
Bajibabu Bollepalli, Lauri Juvela, Paavo Alku
Recent studies have shown that text-to-speech synthesis quality can be improved by using glottal vocoding. This refers to vocoders that parameterize speech into two parts, the glot…
Deep Learning for Tube Amplifier Emulation
Eero-Pekka Damskägg, Lauri Juvela, Etienne Thuillier +1
Analog audio effects and synthesizers often owe their distinct sound to circuit nonlinearities. Faithfully modeling such significant aspect of the original sound in virtual analog…
Waveform generation for text-to-speech synthesis using pitch-synchronous multi-scale generative adversarial networks
Lauri Juvela, Bajibabu Bollepalli, Junichi Yamagishi +1
The state-of-the-art in text-to-speech synthesis has recently improved considerably due to novel neural waveform generation methods, such as WaveNet. However, these methods suffer…
Speaker-independent raw waveform model for glottal excitation
Lauri Juvela, Vassilis Tsiaras, Bajibabu Bollepalli +3
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…
A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis
Xin Wang, Jaime Lorenzo-Trueba, Shinji Takaki +2
Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in ac…
Speech waveform synthesis from MFCC sequences with generative adversarial networks
Lauri Juvela, Bajibabu Bollepalli, Xin Wang +4
This paper proposes a method for generating speech from filterbank mel frequency cepstral coefficients (MFCC), which are widely used in speech applications, such as ASR, but are ge…