Related papers: Personalized Adaptation with Pre-trained Speech En…

Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text. Important non-textual speech variation is seldom annotated, in which case output control must be learned in an…

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…

Traditionally, in paralinguistic analysis for emotion detection from speech, emotions have been identified with discrete or dimensional (continuous-valued) labels. Accordingly, models that have been proposed for emotion detection use one or…

Performance in Speech Emotion Recognition (SER) on a single language has increased greatly in the last few years thanks to the use of deep learning techniques. However, cross-lingual SER remains a challenge in real-world applications due to…

In this work, we explore the dependencies between speaker recognition and emotion recognition. We first show that knowledge learned for speaker recognition can be reused for emotion recognition through transfer learning. Then, we show the…

This paper proposes a personalization method for speech emotion recognition (SER) through in-context learning (ICL). Since the expression of emotions varies from person to person, speaker-specific adaptation is crucial for improving the SER…

Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of…

Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training methods have been proposed. Among these methods, Masked…

Recently, variational autoencoders have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. However, variational autoencoders are trained on clean speech only, which…

Emotion recognition in conversations (ERC) is challenging due to the multimodal nature of the emotion expression. In this paper, we propose to pretrain a text-based recognition model from unsupervised speech transcripts with LLM guidance.…

Learning speaker-specific features is vital in many applications like speaker recognition, diarization and speech recognition. This paper provides a novel approach, we term Neural Predictive Coding (NPC), to learn speaker-specific…

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.…

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…

In this paper, we investigate the usage of autoencoders in modeling textual data. Traditional autoencoders suffer from at least two aspects: scalability with the high dimensionality of vocabulary size and dealing with task-irrelevant words.…

Emotion recognition from speech is one of the key steps towards emotional intelligence in advanced human-machine interaction. Identifying emotions in human speech requires learning features that are robust and discriminative across diverse…

Cross-lingual speech emotion recognition (SER) remains a challenging task due to differences in phonetic variability and speaker-specific expressive styles across languages. Effectively capturing emotion under such diverse conditions…

We propose a method for speech-to-speech emotionpreserving translation that operates at the level of discrete speech units. Our approach relies on the use of multilingual emotion embedding that can capture affective information in a…

Speaker recognition deals with recognizing speakers by their speech. Most speaker recognition systems are built upon two stages, the first stage extracts low dimensional correlation embeddings from speech, and the second performs the…

Self supervised representation learning has recently attracted a lot of research interest for both the audio and visual modalities. However, most works typically focus on a particular modality or feature alone and there has been very…