A new study developed a snore-source classification model that uses STFT spectrograms, pretrained CNN features, and an L2-regularized SVM to identify where snoring originates in the upper airway.
Recent speech-aware large language models (Speech-LLMs) rely on a pre-trained speech encoder to convert audio into semantic-rich representations consumable by LLM. In this work, instead, we explore: ...
Abstract: Ultra-low-bitrate speech coding is pivotal for bandwidth-constrained communication and deep compression, yet maintaining naturalness and speaker identity at such extreme bit budgets remains ...
WavTTS is an end-to-end zero-shot TTS framework that generates speech directly in the raw waveform space, without relying on intermediate acoustic representations such as mel-spectrograms, VAE latents ...
Abstract: In this work, we propose CleanMel, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance ...
Speech Emotion Recognition (SER) is crucial for enhancing human-computer interactions by enabling machines to understand and respond appropriately to human emotions. However, accurately recognizing ...
Each class includes 500 wav files with a length of about 30s. Vietnam Traditional Music (5 genres): https://www.kaggle.com/datasets/homata123/vntm-for-building-model ...
Text to speech (TTS) has attracted a lot of attention recently due to advancements in deep learning. Neural network-based TTS models (such as Tacotron 2, DeepVoice 3 and Transformer TTS) have ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results