相关论文: Learning De-identified Representations of Prosody …

The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly.…

Spoken language understanding research to date has generally carried a heavy text perspective. Most datasets are derived from text, which is then subsequently synthesized into speech, and most models typically rely on automatic…

Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform. The development of high-performing neural network sound recognition systems has raised the possibility of…

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content…

In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features…

Audio deepfakes are increasingly in-differentiable from organic speech, often fooling both authentication systems and human listeners. While many techniques use low-level audio features or optimization black-box model training, focusing on…

Voice conversion is the task to transform voice characteristics of source speech while preserving content information. Nowadays, self-supervised representation learning models are increasingly utilized in content extraction. However, in…

The goal of this contribution is to use a parametric speech synthesis system for reducing background noise and other interferences from recorded speech signals. In a first step, Hidden Markov Models of the synthesis system are trained. Two…

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore unsupervised…

Recent neural speech synthesis systems have gradually focused on the control of prosody to improve the quality of synthesized speech, but they rarely consider the variability of prosody and the correlation between prosody and semantics…

The primary characteristic of robust speaker representations is that they are invariant to factors of variability not related to speaker identity. Disentanglement of speaker representations is one of the techniques used to improve…

Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but…

The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene…

Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…

Existing contrastive learning methods for anomalous sound detection refine the audio representation of each audio sample by using the contrast between the samples' augmentations (e.g., with time or frequency masking). However, they might be…

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of…

A text-to-speech (TTS) model typically factorizes speech attributes such as content, speaker and prosody into disentangled representations.Recent works aim to additionally model the acoustic conditions explicitly, in order to disentangle…

The rapid spread of media content synthesis technology and the potentially damaging impact of audio and video deepfakes on people's lives have raised the need to implement systems able to detect these forgeries automatically. In this work…