arXiv research

This paper examines the speaker identification potential of breath sounds in continuous speech. Speech is largely produced during exhalation. In order to replenish air in the lungs, speakers must periodically inhale. When inhalation occurs in the midst of continuous speech, it is generally through the mouth. Intra-spee…

Recent deep learning approaches have achieved impressive performance on speech enhancement and separation tasks. However, these approaches have not been investigated for separating mixtures of arbitrary sounds of different types, a task we refer to as universal sound separation, and it is unknown how performance on spe…

Paper aims to find joint representation between vocal tract geometry and speech sound acoustics.

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 methods of waveform generation. The similarity between speech and music audio synthesis techniques suggests interesting avenues to explore in te…

We propose a learning-based filter that allows us to directly modify a synthetic speech waveform into a natural speech waveform. Speech-processing systems using a vocoder framework such as statistical parametric speech synthesis and voice conversion are convenient especially for a limited number of data because it is p…

Given the recent surge in developments of deep learning, this article provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered side-by-side, in order to point out similarities and differences between the domains, hig…

Stabilizes training of DNN for speech enhancement using PESQ scores.

Study investigates how simple speech sounds can form abstract categories.

This paper proposes a method that allows non-parallel many-to-many voice conversion (VC) by using a variant of a generative adversarial network (GAN) called StarGAN. Our method, which we call StarGAN-VC, is noteworthy in that it (1) requires no parallel utterances, transcriptions, or time alignment procedures for speec…

SpecGrad improves neural vocoder sound quality by adapting diffusion noise to log-mel spectrogram.

Deep learning approaches have recently achieved impressive performance on both audio source separation and sound classification. Most audio source separation approaches focus only on separating sources belonging to a restricted domain of source classes, such as speech and music. However, recent work has demonstrated th…

Speech-related Brain Computer Interface (BCI) technologies provide effective vocal communication strategies for controlling devices through speech commands interpreted from brain signals. In order to infer imagined speech from active thoughts, we propose a novel hierarchical deep learning BCI system for subject-indepen…

Deep learning maps tongue movements to speech sounds for voiceless individuals.

In this work, we train fully convolutional networks to detect anger in speech. Since training these deep architectures requires large amounts of data and the size of emotion datasets is relatively small, we use transfer learning. However, unlike previous approaches that use speech or emotion-based tasks for the source …

This paper addresses the problem of localizing audio sources using binaural measurements. We propose a supervised formulation that simultaneously localizes multiple sources at different locations. The approach is intrinsically efficient because, contrary to prior work, it relies neither on source separation, nor on mon…

Grad-TTS models speech from text using diffusion probabilistic techniques.

Improves naturalness in TTS samples using quantized VAE and auto-regressive prosody.

Speech separation has been very successful with deep learning techniques. Substantial effort has been reported based on approaches over spectrogram, which is well known as the standard time-and-frequency cross-domain representation for speech signals. It is highly correlated to the phonetic structure of speech, or "how…

End-to-end Sanskrit TTS developed with limited data, achieving good quality.

Optimal transport as a loss for machine learning optimization problems has recently gained a lot of attention. Building upon recent advances in computational optimal transport, we develop an optimal transport non-negative matrix factorization (NMF) algorithm for supervised speech blind source separation (BSS). Optimal …

With latent variables, stochastic recurrent models have achieved state-of-the-art performance in modeling sound-wave sequence. However, opposite results are also observed in other domains, where standard recurrent networks often outperform stochastic models. To better understand this discrepancy, we re-examine the role…

Study improves radio show segmentation using audio embeddings.

A-StarGAN improves nonparallel voice conversion speed and realism.

While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio source separation algorithms to more general domains such as environmental monitori…

Generative Adversarial Networks (GANs) have become exceedingly popular in a wide range of data-driven research fields, due in part to their success in image generation. Their ability to generate new samples, often from only a small amount of input data, makes them an exciting research tool in areas with limited data re…

This paper proposes a non-parallel many-to-many voice conversion (VC) method using a variant of the conditional variational autoencoder (VAE) called an auxiliary classifier VAE (ACVAE). The proposed method has three key features. First, it adopts fully convolutional architectures to construct the encoder and decoder ne…

A new framework enhances binaural audio for moving talkers.

An increasing number of datasets contain multiple views, such as video, sound and automatic captions. A basic challenge in representation learning is how to leverage multiple views to learn better representations. This is further complicated by the existence of a latent alignment between views, such as between speech a…

This paper describes a versatile method that accelerates multichannel source separation methods based on full-rank spatial modeling. A popular approach to multichannel source separation is to integrate a spatial model with a source model for estimating the spatial covariance matrices (SCMs) and power spectral densities…

We propose a training method for deep neural network (DNN)-based source enhancement to increase objective sound quality assessment (OSQA) scores such as the perceptual evaluation of speech quality (PESQ). In many conventional studies, DNNs have been used as a mapping function to estimate time-frequency masks and traine…

Efficient neural network for audio source separation.

Most speech recognition tasks pertain to mapping words across two modalities: acoustic and orthographic. In this work, we suggest learning encoders that map variable-length, acoustic or phonetic, sequences that represent words into fixed-dimensional vectors in a shared latent space; such that the distance between two w…

Inspired by brain's modality fusion, this paper detects active speakers from audio and video.

As the technology is advancing, audio recognition in machine learning is improved as well. Research in audio recognition has traditionally focused on speech. Living creatures (especially the small ones) are part of the whole ecosystem, monitoring as well as maintaining them are important tasks. Species such as animals …

The task of estimating the fundamental frequency of a monophonic sound recording, also known as pitch tracking, is fundamental to audio processing with multiple applications in speech processing and music information retrieval. To date, the best performing techniques, such as the pYIN algorithm, are based on a combinat…

Deep learning methods have achieved high performance in sound recognition tasks. Deciding how to feed the training data is important for further performance improvement. We propose a novel learning method for deep sound recognition: Between-Class learning (BC learning). Our strategy is to learn a discriminative feature…

This paper proposes a novel optimization principle and its implementation for unsupervised anomaly detection in sound (ADS) using an autoencoder (AE). The goal of unsupervised-ADS is to detect unknown anomalous sound without training data of anomalous sound. Use of an AE as a normal model is a state-of-the-art techniqu…

Many-to-Many VTN improves voice conversion across multiple speakers.

Recurrent Networks are one of the most powerful and promising artificial neural network algorithms to processing the sequential data such as natural languages, sound, time series data. Unlike traditional feed-forward network, Recurrent Network has a inherent feed back loop that allows to store the temporal context info…

Paper presents an audiovisual model to recognize sounds from weakly labeled video data.

Neural network synthesizes percussive sounds with adjustable timbral features.

This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce exactly the same speech even if we try to express the same linguistic and para-linguistic information, typical statistical speech synthesis pr…

This paper introduces a new dataset called "ToyADMOS" designed for anomaly detection in machine operating sounds (ADMOS). To the best our knowledge, no large-scale datasets are available for ADMOS, although large-scale datasets have contributed to recent advancements in acoustic signal processing. This is because anoma…

Singing voice conversion is a task to convert a song sang by a source singer to the voice of a target singer. In this paper, we propose using a parallel data free, many-to-one voice conversion technique on singing voices. A phonetic posterior feature is first generated by decoding singing voices through a robust Automa…

A new method detects anomalous sounds using self-supervised learning.

In this study we present a kernel based convolution model to characterize neural responses to natural sounds by decoding their time-varying acoustic features. The model allows to decode natural sounds from high-dimensional neural recordings, such as magnetoencephalography (MEG), that track timing and location of human …

In this paper we demonstrate end-to-end continuous speech recognition (CSR) using electroencephalography (EEG) signals with no speech signal as input. An attention model based automatic speech recognition (ASR) and connectionist temporal classification (CTC) based ASR systems were implemented for performing recognition…

Detects AI-synthesized speech using cepstral and bispectral analysis.