Related papers: On the Use of Self-Supervised Representation Learn…
Underperformance of ASR systems for speakers of African American Vernacular English (AAVE) and other marginalized language varieties is a well-documented phenomenon, and one that reinforces the stigmatization of these varieties. We…
Unsupervised representation learning for speech processing has matured greatly in the last few years. Work in computer vision and natural language processing has paved the way, but speech data offers unique challenges. As a result, methods…
Overlapped speech is notoriously problematic for speaker diarization systems. Consequently, the use of speech separation has recently been proposed to improve their performance. Although promising, speech separation models struggle with…
Speaker Diarization is the problem of separating speakers in an audio. There could be any number of speakers and final result should state when speaker starts and ends. In this project, we analyze given audio file with 2 channels and 2…
There are several domains that own corresponding widely used feature extractors, such as ResNet, BERT, and GPT-x. These models are usually pre-trained on large amounts of unlabeled data by self-supervision and can be effectively applied to…
It was shown in literature that speech representations extracted by self-supervised pre-trained models exhibit similarities with brain activations of human for speech perception and fine-tuning speech representation models on downstream…
Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…
Preserving a patient's identity is a challenge for automatic, speech-based diagnosis of mental health disorders. In this paper, we address this issue by proposing adversarial disentanglement of depression characteristics and speaker…
Existing studies on self-supervised speech representation learning have focused on developing new training methods and applying pre-trained models for different applications. However, the quality of these models is often measured by the…
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,…
Neural speech separation has made remarkable progress and its integration with automatic speech recognition (ASR) is an important direction towards realizing multi-speaker ASR. This work provides an insightful investigation of speech…
We study multi-task learning for two orthogonal speech technology tasks: speech and speaker recognition. We use wav2vec2 as a base architecture with two task-specific output heads. We experiment with different architectural decisions to mix…
It was shown that pre-trained models with self-supervised learning (SSL) techniques are effective in various downstream speech tasks. However, most such models are trained on single-speaker speech data, limiting their effectiveness in…
Self-supervised representation learning for speech often involves a quantization step that transforms the acoustic input into discrete units. However, it remains unclear how to characterize the relationship between these discrete units and…
Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others. While the features are undeniably useful in speech…
Self-supervision has shown great potential for audio-visual speech recognition by vastly reducing the amount of labeled data required to build good systems. However, existing methods are either not entirely end-to-end or do not train joint…
Speaker Change Detection (SCD) is to identify boundaries among speakers in a conversation. Motivated by the success of fine-tuning wav2vec 2.0 models for the SCD task, a further investigation of self-supervised learning (SSL) features for…
State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…
Speaker diarization systems segment a conversation recording based on the speakers' identity. Such systems can misclassify the speaker of a portion of audio due to a variety of factors, such as speech pattern variation, background noise,…
Self-supervised speech representation learning has recently been a prosperous research topic. Many algorithms have been proposed for learning useful representations from large-scale unlabeled data, and their applications to a wide range of…