Related papers: Normalization through Fine-tuning: Understanding W…

Recent studies have shown how self-supervised models can produce accurate speech quality predictions. Speech representations generated by the pre-trained wav2vec 2.0 model allows constructing robust predicting models using small amounts of…

Recent advances in unsupervised speech representation learning discover new approaches and provide new state-of-the-art for diverse types of speech processing tasks. This paper presents an investigation of using wav2vec 2.0 deep speech…

What do deep neural speech models know about phonology? Existing work has examined the encoding of individual linguistic units such as phonemes in these models. Here we investigate interactions between units. Inspired by classic experiments…

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

A deep Transformer model with good evaluation score does not mean each subnetwork (a.k.a transformer block) learns reasonable representation. Diagnosing abnormal representation and avoiding it can contribute to achieving a better evaluation…

Modern phonetic research regularly makes use of automatic tools for the annotation of speech data, however few tools exist for the annotation of many variable phonetic phenomena. At the same time, pre-trained self-supervised models, such as…

Self-supervised learning approaches have lately achieved great success on a broad spectrum of machine learning problems. In the field of speech processing, one of the most successful recent self-supervised models is wav2vec 2.0. In this…

Conventional spoofing detection systems have heavily relied on the use of handcrafted features derived from speech data. However, a notable shift has recently emerged towards the direct utilization of raw speech waveforms, as demonstrated…

Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve…

We propose a method for emotion recognition through emotiondependent speech recognition using Wav2vec 2.0. Our method achieved a significant improvement over most previously reported results on IEMOCAP, a benchmark emotion dataset.…

Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production…

Learning music representations that are general-purpose offers the flexibility to finetune several downstream tasks using smaller datasets. The wav2vec 2.0 speech representation model showed promising results in many downstream speech…

Self-supervised learning methods such as wav2vec 2.0 have shown promising results in learning speech representations from unlabelled and untranscribed speech data that are useful for speech recognition. Since these representations are…

Accurate speech emotion recognition is essential for developing human-facing systems. Recent advancements have included finetuning large, pretrained transformer models like Wav2Vec 2.0. However, the finetuning process requires substantial…

Enabling machines to respond appropriately to natural language commands could greatly expand the number of people to whom they could be of service. Recently, advances in neural network-trained word embeddings have empowered non-embodied…

Fine-tuning speech representation models can enhance performance on specific tasks but often compromises their cross-task generalization ability. This degradation is often caused by excessive changes in the representations, making it…

Self-supervised models for speech representation learning now see widespread use for their versatility and performance on downstream tasks, but the effect of model architecture on the linguistic information learned in their representations…

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…

Recent advances in neural text-to-speech research have been dominated by two-stage pipelines utilizing low-level intermediate speech representation such as mel-spectrograms. However, such predetermined features are fundamentally limited,…

In this work, we propose a speaker anonymization pipeline that leverages high quality automatic speech recognition and synthesis systems to generate speech conditioned on phonetic transcriptions and anonymized speaker embeddings. Using…