相关论文: Speech transformer models for extracting informati…

Pretrained contextualized text representation models learn an effective representation of a natural language to make it machine understandable. After the breakthrough of the attention mechanism, a new generation of pretrained models have…

Recognizing human non-speech vocalizations is an important task and has broad applications such as automatic sound transcription and health condition monitoring. However, existing datasets have a relatively small number of vocal sound…

Language models are typically trained on large corpora of text in their default orthographic form. However, this is not the only option; representing data as streams of phonemes can offer unique advantages, from deeper insights into…

As generative AI systems become competent and democratized in science, business, and government, deeper insight into their failure modes now poses an acute need. The occasional volatility in their behavior, such as the propensity of…

Large self-supervised pre-trained speech models have achieved remarkable success across various speech-processing tasks. The self-supervised training of these models leads to universal speech representations that can be used for different…

The safety of children in children home has become an increasing social concern, and the purpose of this experiment is to use machine learning applied to detect the scenarios of child abuse to increase the safety of children. This…

While behaviors of pretrained language models (LMs) have been thoroughly examined, what happened during pretraining is rarely studied. We thus investigate the developmental process from a set of randomly initialized parameters to a…

Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be…

Learning the latent representation of data in unsupervised fashion is a very interesting process that provides relevant features for enhancing the performance of a classifier. For speech emotion recognition tasks, generating effective…

Speech emotion recognition (SER), the task of identifying the expression of emotion from spoken content, is challenging due to the difficulty in extracting representations that capture emotional attributes from speech. The scarcity of…

Pretrained self-supervised speech models excel in speech tasks but do not reflect the hierarchy of human speech processing, as they encode rich semantics in middle layers and poor semantics in late layers. Recent work showed that…

Child-centered daylong recordings are essential for studying early language development, but existing speech models trained on clean adult data perform poorly due to acoustic and linguistic differences. We introduce BabyHuBERT, a…

Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and…

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…

Brain signals accompany various information relevant to human actions and mental imagery, making them crucial to interpreting and understanding human intentions. Brain-computer interface technology leverages this brain activity to generate…

Recent advances in audio-language models have demonstrated remarkable success on short, segment-level speech tasks. However, real-world applications such as meeting transcription, spoken document understanding, and conversational analysis…

Speech Emotion Recognition is a crucial area of research in human-computer interaction. While significant work has been done in this field, many state-of-the-art networks struggle to accurately recognize emotions in speech when the data is…

The emergence of deep learning networks raises a need for explainable AI so that users and domain experts can be confident applying them to high-risk decisions. In this paper, we leverage data from the latent space induced by deep learning…

Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. Nonetheless, without sufficient data, seq2seq VC models can suffer from unstable training and mispronunciation problems in…

Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language. Recent attempts to adapt diffusion to language have…