Related papers: Sounding Like a Winner? Prosodic Differences in Po…

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…

Singing voice synthesis (SVS) has seen remarkable advancements in recent years. However, compared to speech and general audio data, publicly available singing datasets remain limited. In practice, this data scarcity often leads to…

Speaker identity is one of the important characteristics of human speech. In voice conversion, we change the speaker identity from one to another, while keeping the linguistic content unchanged. Voice conversion involves multiple speech…

In this work, we study the hypothesis that speaker identity embeddings extracted from speech samples may be used for detection and classification of emotion. In particular, we show that emotions can be effectively identified by learning…

Recent self-supervised learning (SSL) models have proven to learn rich representations of speech, which can readily be utilized by diverse downstream tasks. To understand such utilities, various analyses have been done for speech SSL models…

Recent advances in deep learning methods have elevated synthetic speech quality to human level, and the field is now moving towards addressing prosodic variation in synthetic speech.Despite successes in this effort, the state-of-the-art…

Recent developments in pre-trained speech representation utilizing self-supervised learning (SSL) have yielded exceptional results on a variety of downstream tasks. One such technique, known as masked predictive coding (MPC), has been…

As the technology advances, an ample amount of data is collected in sports with the help of advanced sensors. Sports Analytics is the study of this data to provide a constructive advantage to the team and its players. The game of…

This paper proposes an Expressive Speech Synthesis model that utilizes token-level latent prosodic variables in order to capture and control utterance-level attributes, such as character acting voice and speaking style. Current works aim to…

Prosodic features such as pitch, timing, and intonation are central to spoken communication, conveying emotion, intent, and discourse structure. In text-based settings, where these cues are absent, emojis act as visual surrogates that add…

Audio and speech self-supervised encoder models are now widely used for a lot of different tasks. Many of these models are often trained on clean segmented speech content such as LibriSpeech. In this paper, we look into how the pretraining…

Prosodic boundaries in speech are of great relevance to both speech synthesis and audio annotation. In this paper, we apply the wav2vec 2.0 framework to the task of detecting these boundaries in speech signal, using only acoustic…

Collaborative competitions have gained popularity in the scientific and technological fields. These competitions involve defining tasks, selecting evaluation scores, and devising result verification methods. In the standard scenario,…

The performance of sentence encoders can be significantly improved through the simple practice of fine-tuning using contrastive loss. A natural question arises: what characteristics do models acquire during contrastive learning? This paper…

In the recent years, singing voice separation systems showed increased performance due to the use of supervised training. The design of training datasets is known as a crucial factor in the performance of such systems. We investigate on how…

Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…

Recent work in the domain of speech enhancement has explored the use of self-supervised speech representations to aid in the training of neural speech enhancement models. However, much of this work focuses on using the deepest or final…

Many neural network speaker recognition systems model each speaker using a fixed-dimensional embedding vector. These embeddings are generally compared using either linear or 2nd-order scoring and, until recently, do not handle…

Our prior experiments show that humans and machines seem to employ different approaches to speaker discrimination, especially in the presence of speaking style variability. The experiments examined read versus conversational speech.…

Recent advancements in Deep and Self-Supervised Learning (SSL) have led to substantial improvements in Speech Emotion Recognition (SER) performance, reaching unprecedented levels. However, obtaining sufficient amounts of accurately labeled…