11 accepted papers
Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Many style-transfer-inspired methods such as generative adversarial networks (GANs) and variational autoencoders (VAEs) have been proposed. Recently, AutoVC, a conditional autoencoders (CAEs) ba…
The speech transmission index (STI) of a listening position within a given room indicates the quality and intelligibility of speech uttered in that room. The measure is very reliable for predicting speech intelligibility in many room conditions but requires an STI measurement of the impulse response…
Automated objective methods of audio source separation evaluation are fast, cheap, and require little effort by the investigator. However, their output often correlates poorly with human quality assessments and typically require ground-truth (perfectly separated) signals to evaluate algorithm perfor…
We introduce FFTNet, a deep learning approach synthesizing audio waveforms. Our approach builds on the recent WaveNet project, which showed that it was possible to synthesize a natural sounding audio waveform directly from a deep convolutional neural network. FFTNet offers two improvements over Wave…
State-of-the art voice conversion methods re-synthesize voice from spectral representations such as MFCCs and STRAIGHT, thereby introducing muffled artifacts. We propose a method that circumvents this concern using concatenative synthesis coupled with exemplar-based unit selection. Given parallel sp…
When different parts of speech content such as voice-overs and narration are recorded in real-world environments with different acoustic properties and background noise, the difference in sound quality between the recordings is typically quite audible and therefore undesirable. We propose an algorit…
Automated objective methods of audio evaluation are fast, cheap, and require little effort by the investigator. However, objective evaluation methods do not exist for the output of all audio processing algorithms, often have output that correlates poorly with human quality assessments, and require g…
For the music structure segmentation task, one wants to solve two co-existing but sometimes contradicting problems; find global repetitive/homogenous structures and locate accurate local change points. In this paper we propose two algorithms to address these two problems. The algorithms can independ…
We propose an efficient technique to learn probabilistic hierarchical topic models that are designed to preserve the manifold structure of audio data. The consideration of the data manifold is important, as it has been shown to provide superior performance in certain audio applications such as sourc…
Desirable properties of real-world speech enhancement methods include online operation, single-channel operation, operation in the presence of a variety of noise types including non-stationary noise, and no requirement for isolated training examples of the specific speaker and noise type at hand. Me…
We present a general single-channel speech dereverberation method based on an explicit generative model of reverberant and noisy speech. To regularize the model, we use a pre-learned speech model of clean and dry speech as a prior and perform posterior inference over the latent clean speech. The rev…